Daily Papers

As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications. We introduce HealthAgentBench, a suite of 54 agentic healthcare tasks across 7 categories each with its unique environment. The benchmark suite spans diverse workflows throughout the patient journey and a broad range of modalities. Each task is designed to replicate an end-to-end clinical workflow: given minimal instructions, an agent must explore raw healthcare data, operate within a complex environment, and execute multi-step solutions that go beyond naive prompting. A final task success rate is reported to provide a single, interpretable metric for HealthAgentBench overall performance for each agent. Evaluating frontier agents on HealthAgentBench, we find that overall task success rate remains low, underscoring the difficulty of the suite. The strongest and the most cost effective agent, Codex GPT-5.5, achieves only approximately 42% success rate. Beyond aggregate performance, HealthAgentBench reveals nuanced strengths and weaknesses across task categories. Frontier agents show promise in automatically developing research modeling pipelines over EHR data, but medical imaging remains especially challenging, particularly for Claude Code models, while Codex GPT-5.5 shows emerging capability. Tasks that combine large search spaces with compositional reasoning requirements remain difficult for all current agents. Together, these results suggest that HealthAgentBench provides a challenging and realistic benchmark with substantial room for future progress. We release our benchmark at https://github.com/microsoft/HealthAgentBench.

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons.

Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation. Our integrated approach leverages intent clarification, retrieval-augmented generation, and specialized sub-agents orchestrated via Claude's agent framework. We demonstrate that this method significantly improves the accuracy and reliability of code assistants in real-world repositories, yielding higher single-shot success rates and better adherence to project context than baseline single-agent approaches. Qualitative results on a large Next.js codebase show the multi-agent system effectively plans, edits, and tests complex features with minimal human intervention. We compare our system with recent frameworks like CodePlan, MASAI, and HyperAgent, highlighting how targeted context injection and agent role decomposition lead to state-of-the-art performance. Finally, we discuss the implications for deploying LLM-based coding assistants in production, along with lessons learned on context management and future research directions.

Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain specialization methods for LLMs to learn and utilize domain knowledge and data. However, existing domain-specific code benchmarks cannot evaluate the effectiveness of domain specialization methods, which focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge, lacking explicit knowledge corpora for developing domain specialization methods. To this end, we present KOCO-BENCH, a novel benchmark designed for evaluating domain specialization methods in real-world software development. KOCO-BENCH contains 6 emerging domains with 11 software frameworks and 25 projects, featuring curated knowledge corpora alongside multi-granularity evaluation tasks including domain code generation (from function-level to project-level with rigorous test suites) and domain knowledge understanding (via multiple-choice Q&A). Unlike previous benchmarks that only provide test sets for direct evaluation, KOCO-BENCH requires acquiring and applying diverse domain knowledge (APIs, rules, constraints, etc.) from knowledge corpora to solve evaluation tasks. Our evaluations reveal that KOCO-BENCH poses significant challenges to state-of-the-art LLMs. Even with domain specialization methods (e.g., SFT, RAG, kNN-LM) applied, improvements remain marginal. Best-performing coding agent, Claude Code, achieves only 34.2%, highlighting the urgent need for more effective domain specialization methods. We release KOCO-BENCH, evaluation code, and baselines to advance further research at https://github.com/jiangxxxue/KOCO-bench.

We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos Preview, Opus 4.7 Preview, Opus 4.6, and Sonnet 4.6): an unprompted sabotage evaluation testing model behaviour with opportunities to sabotage safety research, and a sabotage continuation evaluation testing whether models continue to sabotage when placed in trajectories where prior actions have started undermining research. We find no instances of unprompted sabotage across any model, with refusal rates close to zero for Mythos Preview and Opus 4.7 Preview, though all models sometimes only partially completed tasks. In the continuation evaluation, Mythos Preview actively continues sabotage in 7% of cases (versus 3% for Opus 4.6, 4% for Sonnet 4.6, and 0% for Opus 4.7 Preview), and exhibits reasoning-output discrepancy in the majority of these cases, indicating covert sabotage reasoning. Our evaluation framework builds on Petri, an open-source LLM auditing tool, with a custom scaffold running models inside Claude Code, alongside an iterative pipeline for generating realistic sabotage trajectories. We measure both evaluation awareness and a new form of situational awareness termed "prefill awareness", the capability to recognise that prior trajectory content was not self-generated. Opus 4.7 Preview shows notably elevated unprompted evaluation awareness, while prefill awareness remains low across all models. Finally, we discuss limitations including evaluation awareness confounds, limited scenario coverage, and untested pathways to risk beyond safety research sabotage.

Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing benchmarks often focus on algorithmic problems or Python-centric bug fixing, leaving critical dimensions of software engineering underexplored. To address these gaps, we introduce SWE-Compass1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework. SWE-Compass spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests and refined through systematic filtering and validation. We benchmark ten state-of-the-art LLMs under two agentic frameworks, SWE-Agent and Claude Code, revealing a clear hierarchy of difficulty across task types, languages, and scenarios. Moreover, by aligning evaluation with real-world developer practices, SWE-Compass provides a rigorous and reproducible foundation for diagnosing and advancing agentic coding capabilities in large language models.

Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-observability decision-making. We first report our Gemini Plays Pokemon (GPP) experiments. With iterative human-in-the-loop harness refinement, GPP became the first AI system to complete Pokemon Blue, Yellow Legacy on hard mode, and Crystal without a lost battle. In the hardest stages, the agent itself began iterating on its strategy through long-context memory, surfacing emergent self-improvement signals alongside human-in-the-loop refinement. Continual Harness removes the human fully from this loop: a reset-free self-improving harness for embodied agents that formalizes and automates what we observed. Starting from only a minimal environment interface, the agent alternates between acting and refining its own prompt, sub-agents, skills, and memory, drawing on any past trajectory data. Prompt-optimization methods require episode resets; Continual Harness adapts online within a single run. On Pokemon Red and Emerald across frontier models, Continual Harness starting from scratch substantially reduces button-press cost relative to the minimalist baseline and recovers a majority of the gap to a hand-engineered expert harness, with capability-dependent gains, despite starting from the same raw interface with no curated knowledge, no hand-crafted tools, and no domain scaffolding. We then close the loop with the model itself: an online process-reward co-learning loop, in which an open-source agent's rollouts through the refining harness are relabeled by a frontier teacher and used to update the model, drives sustained in-game milestone progress on Pokemon Red without resetting the environment between training iterations.

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a distinct safety challenge in that harmful behavior may emerge through sequences of individually plausible steps, including intermediate actions that appear locally acceptable but collectively lead to unauthorized actions. We present AgentHazard, a benchmark for evaluating harmful behavior in computer-use agents. AgentHazard contains 2,653 instances spanning diverse risk categories and attack strategies. Each instance pairs a harmful objective with a sequence of operational steps that are locally legitimate but jointly induce unsafe behavior. The benchmark evaluates whether agents can recognize and interrupt harm arising from accumulated context, repeated tool use, intermediate actions, and dependencies across steps. We evaluate AgentHazard on Claude Code, OpenClaw, and IFlow using mostly open or openly deployable models from the Qwen3, Kimi, GLM, and DeepSeek families. Our experimental results indicate that current systems remain highly vulnerable. In particular, when powered by Qwen3-Coder, Claude Code exhibits an attack success rate of 73.63\%, suggesting that model alignment alone does not reliably guarantee the safety of autonomous agents.

Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose GEMS (Agent-Native Multimodal GEneration with Memory and Skills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.

As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, bypassing the task of locating affected tests from the full project and excluding the need for new tests entirely. We present TEBench, the first project-level benchmark for test evolution. Given a project repository and a code-changing commit, TEBench requires systems to autonomously identify tests requiring modification, determine where new tests are needed, and produce the corresponding test patch. We construct TEBench through a four-stage pipeline over Defects4J projects, curating 314 task instances from 10 projects with developer-written ground truth. Each instance is annotated with one or more of three evolution types: Test-Breaking (tests that fail), Test-Stale (tests that pass but no longer meaningfully validate updated behavior), and Test-Missing (new tests needed for introduced behavior). We evaluate seven configurations spanning three industrial agent frameworks (Claude Code, Codex CLI, OpenCode) and six base models, alongside a heuristic baseline. All seven configurations converge on an identification F1 of 45.7% to 49.4%, revealing a shared performance ceiling across both frameworks and base models. Test-Stale is the most challenging type, averaging F1 around 36%, since configurations rely on execution failure signals and lack proactive semantic reasoning. On the update task, configurations produce highly executable test modifications whose surface form diverges substantially from ground truth. Trajectory analysis reveals a reactive "execute-fail-fix" loop that succeeds for breaking tests but structurally cannot address stale or missing tests. TEBench is available at https://github.com/iSEngLab/TEBench with a leaderboard at https://tebench-leadership.vercel.app.

Are AI agents tools, co-authors, or researchers? We present a quantified case study (N=1): a physicist supervising an AI coding agent (Claude Code, Sonnet and Opus models) over 12 work days and 57 sessions to build CLAX-PT, a differentiable one-loop perturbation theory module in JAX. We documented and classified 15 supervision events by intervention level. The agent resolved ten autonomously by iterating against oracle tests. Two more by the physicist's domain knowledge. The three it could not -- all evaded oracle detection -- share a common property: the agent treated symptom reduction as root-cause resolution. It spent 33 of the 57 sessions adjusting coefficients within a code architecture that could not represent the target physics, and could not re-evaluate its CLASS-PT branch choice even when prompted to reconsider; only an injected physics concept (anisotropic BAO damping) triggered the redesign. Separately, the agent committed a calibrated correction that passed all oracle tests but corresponded to no quantity in the theory, predicting wrong values at any other cosmology. The fudge factor was caught and replaced within the same session. Three supervision practices proved critical for catching what oracle tests missed: testing at diverse parameter points beyond the fiducial calibration; shared changelogs that surfaced stalled exploration across sessions; and an explicit rule against unphysical numerical patches. In this case, supervision design, not model capability, determined whether the agent's output was trustworthy. Closing the gap would require agents that propose architectural alternatives rather than optimize within a given structure, and distinguish predictive adequacy from explanatory correctness -- capabilities not exhibited here, not obviously addressed by scaling alone. [Abridged.]

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization.

Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current ADS systems use statistical tools designed to be interpretable by humans, rather than interpretable by agents. To address this, we introduce Agentic-imodels, an agentic autoresearch loop that evolves data-science tools designed to be interpretable by agents. Specifically, it develops a library of scikit-learn-compatible regressors for tabular data that are optimized for both predictive performance and a novel LLM-based interpretability metric. The metric measures a suite of LLM-graded tests that probe whether a fitted model's string representation is "simulatable" by an LLM, i.e. whether the LLM can answer questions about the model's behavior by reading its string output alone. We find that the evolved models jointly improve predictive performance and agent-facing interpretability, generalizing to new datasets and new interpretability tests. Furthermore, these evolved models improve downstream end-to-end ADS, increasing performance for Copilot CLI, Claude Code, and Codex on the BLADE benchmark by up to 73%

The AEC-Bench is a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction (AEC) domain. The benchmark covers tasks requiring drawing understanding, cross-sheet reasoning, and construction project-level coordination. This report describes the benchmark motivation, dataset taxonomy, evaluation protocol, and baseline results across several domain-specific foundation model harnesses. We use AEC-Bench to identify consistent tools and harness design techniques that uniformly improve performance across foundation models in their own base harnesses, such as Claude Code and Codex. We openly release our benchmark dataset, agent harness, and evaluation code for full replicability at https://github.com/nomic-ai/aec-bench under an Apache 2 license.

Using Large Language Models (LLMs) has gained popularity among software developers for generating source code. However, the use of LLM-generated code can introduce risks of adding suboptimal, defective, and vulnerable code. This makes it necessary to devise methods for the accurate detection of LLM-generated code. Toward this goal, we perform a case study of Claude 3 Haiku (or Claude 3 for brevity) on CodeSearchNet dataset. We divide our analyses into two parts: function-level and class-level. We extract 22 software metric features, such as Code Lines and Cyclomatic Complexity, for each level of granularity. We then analyze code snippets generated by Claude 3 and their human-authored counterparts using the extracted features to understand how unique the code generated by Claude 3 is. In the following step, we use the unique characteristics of Claude 3-generated code to build Machine Learning (ML) models and identify which features of the code snippets make them more detectable by ML models. Our results indicate that Claude 3 tends to generate longer functions, but shorter classes than humans, and this characteristic can be used to detect Claude 3-generated code with ML models with 82% and 66% accuracies for function-level and class-level snippets, respectively.

Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks. However, their misuse often produces bloated and disorganized code that impairing readability, extensibility, and robustness. Despite this risk, existing benchmarks largely evaluate functional correctness rather than long-term maintainability of code agents. In this paper, we propose SmellBench, an extensible code refactoring benchmark that proactively injects code smells into clean code snippets from real-world repositories. This design enables the generation of controlled, high-quality, and diverse refactoring cases with human-written ground truth. Specifically, it contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories. We further design 3 evaluation aspects covering functional correctness, localization ability, and refactoring quality assessment. Experiments with 2 popular agents and 6 large langauge models (LLMs) show that the best combination - Qwen Code + Claude Sonnet 4.5 - achieved only a 50.34 score of smell elimination. Further analysis reveals that this gap arises from a focus on local code smells and a lack of cross-file understanding, which hinders comprehensive smell elimination.

The dominant industry response to AI-generated code quality problems is to deploy AI reviewers. This paper argues that this response is structurally circular when executable specifications are absent: without an external reference, both the generating agent and the reviewing agent reason from the same artefact, share the same training distribution, and exhibit correlated failures. The review checks code against itself, not against intent. Three hypotheses are developed. First, that correlated errors in homogeneous LLM pipelines echo rather than cancel, a claim supported by convergent empirical evidence from multiple 2025-2026 studies and by three small contrived experiments reported here. The first two experiments are same-family (Claude reviewing Claude-generated code); the third extends to a cross-family panel of four models from three families. All use a planted bug corpus rather than a natural defect sample; they are directional evidence, not a controlled demonstration. Second, that executable specifications perform a domain transition in the Cynefin sense, converting enabling constraints into governing constraints and moving the problem from the complex domain to the complicated domain, a transition that AI makes economically viable at scale. Third, that the defect classes lying outside the reach of executable specifications form a well-defined residual, which is the legitimate and bounded target for AI review. The combined argument implies an architecture: specifications first, deterministic verification pipeline second, AI review only for the structural and architectural residual. This is not a claim that AI review is valueless. It is a claim about what it is actually for, and about what happens when it is deployed without the foundation that makes it non-circular.

Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In this paper, we introduce WizardCoder, which empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code. Through comprehensive experiments on four prominent code generation benchmarks, namely HumanEval, HumanEval+, MBPP, and DS-1000, we unveil the exceptional capabilities of our model. It surpasses all other open-source Code LLMs by a substantial margin. Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+. Our code, model weights, and data are public at https://github.com/nlpxucan/WizardLM

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM code/text generation. We construct a comprehensive benchmark SymBench comprising 37 symbolic tasks with adjustable complexity and also synthesize datasets of 12k multi-round guidance/generation trajectories and 5.5k guidance comparison pairs. We fine-tune the Llama-3-8B model with a newly designed multi-round supervised fine-tuning (SFT) and direct preference optimization (DPO). The resulting model, CodeSteerLLM, augmented with the proposed symbolic and self-answer checkers, effectively guides the code/text generation of larger models. Augmenting GPT-4o with CodeSteer raises its average performance score from 53.3 to 86.4, even outperforming the existing best LLM OpenAI o1 (82.7), o1-preview (74.8), and DeepSeek R1 (76.8) across all 37 tasks (28 seen, 9 unseen). Trained for GPT-4o, CodeSteer demonstrates superior generalizability, providing an average 41.8 performance boost on Claude, Mistral, and GPT-3.5. CodeSteer-guided LLMs fully harness symbolic computing to maintain strong performance on highly complex tasks. Models, Datasets, and Codes are available at https://github.com/yongchao98/CodeSteer-v1.0.

The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from human feedback have enhanced their safety, these methods primarily focus on natural languages, which may not generalize to other domains. This paper introduces CodeAttack, a framework that transforms natural language inputs into code inputs, presenting a novel environment for testing the safety generalization of LLMs. Our comprehensive studies on state-of-the-art LLMs including GPT-4, Claude-2, and Llama-2 series reveal a new and universal safety vulnerability of these models against code input: CodeAttack bypasses the safety guardrails of all models more than 80\% of the time. We find that a larger distribution gap between CodeAttack and natural language leads to weaker safety generalization, such as encoding natural language input with data structures. Furthermore, we give our hypotheses about the success of CodeAttack: the misaligned bias acquired by LLMs during code training, prioritizing code completion over avoiding the potential safety risk. Finally, we analyze potential mitigation measures. These findings highlight new safety risks in the code domain and the need for more robust safety alignment algorithms to match the code capabilities of LLMs.

We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K. In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks.

Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges for data collection and annotation. To address this, current methods often design various data flywheels to gather complex code instructions, enabling models to handle more intricate tasks. However, these approaches typically rely on off-the-shelf datasets and data augmentation from the limited pool of proprietary LLMs (e.g., Claude, GPT4, and so on), which limits the diversity of the constructed data and makes it prone to systemic biases. In this paper, we propose WarriorCoder which learns from expert battles to address these limitations. Specifically, we create an arena for current expert code LLMs, where each model challenges and responds to others' challenges, with evaluations conducted by uninvolved judge models. This competitive framework generates novel training data constructed from scratch, harnessing the strengths of all participants. Experimental results demonstrate that WarriorCoder achieves competitive performance compared to previous methods, even without relying on proprietary LLMs.

The adoption of Large Language Models (LLMs) for code generation in data science offers substantial potential for enhancing tasks such as data manipulation, statistical analysis, and visualization. However, the effectiveness of these models in the data science domain remains underexplored. This paper presents a controlled experiment that empirically assesses the performance of four leading LLM-based AI assistants-Microsoft Copilot (GPT-4 Turbo), ChatGPT (o1-preview), Claude (3.5 Sonnet), and Perplexity Labs (Llama-3.1-70b-instruct)-on a diverse set of data science coding challenges sourced from the Stratacratch platform. Using the Goal-Question-Metric (GQM) approach, we evaluated each model's effectiveness across task types (Analytical, Algorithm, Visualization) and varying difficulty levels. Our findings reveal that all models exceeded a 50% baseline success rate, confirming their capability beyond random chance. Notably, only ChatGPT and Claude achieved success rates significantly above a 60% baseline, though none of the models reached a 70% threshold, indicating limitations in higher standards. ChatGPT demonstrated consistent performance across varying difficulty levels, while Claude's success rate fluctuated with task complexity. Hypothesis testing indicates that task type does not significantly impact success rate overall. For analytical tasks, efficiency analysis shows no significant differences in execution times, though ChatGPT tended to be slower and less predictable despite high success rates. This study provides a structured, empirical evaluation of LLMs in data science, delivering insights that support informed model selection tailored to specific task demands. Our findings establish a framework for future AI assessments, emphasizing the value of rigorous evaluation beyond basic accuracy measures.

Large language models (LLMs) demonstrate strong code generation abilities in general-purpose programming languages but remain limited in specialized domains such as low-level embedded systems programming. This domain involves hardware register manipulation, vendor-specific SDKs, real-time operating system APIs, and hardware abstraction layers that are underrepresented in standard pretraining corpora. We introduce H2LooP Spark Preview, a continual pretraining (CPT) pipeline that adapts the OLMo-3-7B-a fully open language model to the embedded systems domain using BF16 LoRA with rank-stabilized scaling on 8 NVIDIA H100 GPUs. Our training corpus is constructed from repository-datasheet pairs covering 100B tokens of raw embedded systems data across 117 manufacturers, processed using the hierarchical datasheet-to-code mapping approach proposed in SpecMap (Nipane et al., 2026). The resulting curated dataset split contains 23.5B tokens across 13 embedded domains. Continual pretraining with high-rank LoRA (r=512) yields substantial gains, reducing in-domain perplexity by 70.4% and held-out repository perplexity by 66.1%. On generative code completion benchmarks spanning 13 embedded domains, our 7B model outperforms Claude Opus 4.6 and Qwen3-Coder-30B on 8 categories in token accuracy, showing that targeted continual pretraining enables smaller open-weight models to rival frontier systems on specialized technical tasks. We release the production training checkpoint on Huggingface as an open-source artifact.

Large language models (LLMs) have demonstrated strong performance across a wide range of programming tasks, yet their potential for code optimization remains underexplored. This work investigates whether LLMs can optimize the performance of assembly code, where fine-grained control over execution enables improvements that are difficult to express in high-level languages. We present a reinforcement learning framework that trains LLMs using Proximal Policy Optimization (PPO), guided by a reward function that considers both functional correctness, validated through test cases, and execution performance relative to the industry-standard compiler gcc -O3. To support this study, we introduce a benchmark of 8,072 real-world programs. Our model, Qwen2.5-Coder-7B-PPO, achieves 96.0% test pass rates and an average speedup of 1.47x over the gcc -O3 baseline, outperforming all 20 other models evaluated, including Claude-3.7-sonnet. These results indicate that reinforcement learning can unlock the potential of LLMs to serve as effective optimizers for assembly code performance.

Fill-in-the-Middle (FIM) models play a vital role in code completion tasks, leveraging both prefix and suffix context to provide more accurate and contextually relevant suggestions. This paper presents approaches to improve FIM code completion while addressing the challenge of maintaining low latency for real-time coding assistance. We enhance FIM code completion by incorporating context and curriculum examples in the training process. We identify patterns where completion suggestions fail more frequently, revealing complexities that smaller language models struggle with. To address these challenges, we develop a curriculum dataset by extracting hard-to-complete patterns from code repositories and generate context examples using semantic and static analysis tools (e.g. TSC compiler). We fine-tune various sized models, including StarCoder and DeepSeek, on this enhanced dataset. Our evaluation encompasses three key dimensions: the Santa Coder FIM task, the Amazon CCEval benchmark, and a new Multi-Line Infilling evaluation benchmark derived from SWE-bench. Comprehensive ablation studies across multiple model sizes reveal that while all fine-tuned models show improvements, the performance gains are more pronounced for smaller parameter models and incorporating difficult-to-complete examples, as part of curriculum learning, improves the code completion performance. This finding is particularly significant given the latency constraints of code completion tasks. While larger models like GPT and Claude perform well in multi-line completions but are prohibitively challenging to use given high latency, and our fine-tuned models achieve a balance between performance and latency. Finally, we validate our approach through online A/B testing, demonstrating tangible improvements in Completion Acceptance Rate (CAR) and Completion Persistence Rate (CPR), with zero latency impact.

Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on general-purpose libraries or web applications, leaving mobile application development largely unexplored despite its strict platform constraints, framework-driven lifecycles, and complex platform API interactions. We introduce MobileDev-Bench, a benchmark comprising 384 real-world issue-resolution tasks collected from 18 production mobile applications spanning Android Native (Java/Kotlin), React Native (TypeScript), and Flutter (Dart). Each task pairs an authentic developer-reported issue with executable test patches, enabling fully automated validation of model-generated fixes within mobile build environments. The benchmark exhibits substantial patch complexity: fixes modify 12.5 files and 324.9 lines on average, and 35.7% of instances require coordinated changes across multiple artifact types, such as source and manifest files. Evaluation of four state-of-the-art code-capable LLMs, GPT- 5.2, Claude Sonnet 4.5, Gemini Flash 2.5, and Qwen3-Coder, yields low end-to-end resolution rates of 3.39%-5.21%, revealing significant performance gaps compared to prior benchmarks. Further analysis reveals systematic failure modes, with fault localization across multi-file and multi-artifact changes emerging as the primary bottleneck.

Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative for language models, code remains largely unexplored beyond limited quality improvements. We present CodeAlchemy, a synthetic data generation framework that transforms publicly sourced code into semantically-rich training data through 5 strategies: CodeEnhance (quality-aware rewriting), CodeQA (template-based problems), CodeDev (developer tasks), CodeDialogue (multi-turn conversations), and CodeTrace (execution traces). We process 3 corpora across 15 languages to generate 500B+ tokens of synthetic data plus 350B reasoning tokens, orders of magnitude more than prior efforts. CodeTrace instruments and executes 1.3M+ files across 14 languages and 5K libraries, capturing control flow, state tracking, and library knowledge. We introduce DevEval (developer tasks) and TraceEval (execution prediction) benchmarks; frontier models like Claude Sonnet 4.5 achieve only 5.6% exact match on TraceEval, revealing critical gaps in semantic understanding. Our 3B models achieve 83.5% on HumanEval, 63.2% on MBPP, 8.09% win rate on DevEval, and 15.36 ROUGE-2 on TraceEval, outperforming frontier models 10x the size including 27B Gemma-3 and 32B Granite-4.0.

Code large language models (LLMs) have made significant progress in code debugging by directly generating the correct code based on the buggy code snippet. Programming benchmarks, typically consisting of buggy code snippet and their associated test cases, are used to assess the debugging capabilities of LLMs. However, many existing benchmarks primarily focus on Python and are often limited in terms of language diversity (e.g., DebugBench and DebugEval). To advance the field of multilingual debugging with LLMs, we propose the first massively multilingual debugging benchmark, which includes 3.6K test samples of 18 programming languages and covers the automated program repair (APR) task, the code review (CR) task, and the bug identification (BI) task. Further, we introduce the debugging instruction corpora MDEVAL-INSTRUCT by injecting bugs into the correct multilingual queries and solutions (xDebugGen). Further, a multilingual debugger xDebugCoder trained on MDEVAL-INSTRUCT as a strong baseline specifically to handle the bugs of a wide range of programming languages (e.g. "Missing Mut" in language Rust and "Misused Macro Definition" in language C). Our extensive experiments on MDEVAL reveal a notable performance gap between open-source models and closed-source LLMs (e.g., GPT and Claude series), highlighting huge room for improvement in multilingual code debugging scenarios.

Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize functional correctness, overlooking the nuanced requirements found in real-world development. We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions: constraint type, hierarchical levels, and iterative refinement. Built upon a structured taxonomy of 9 categories and 27 constraint types, MultiCodeIF enables granular assessment of both functional and non-functional instruction adherence. Using an automated pipeline, ConstraGen, we synthesize and evolve 2,021 code tasks sourced from 14 programming languages, supporting multi-turn evaluation through feedback-driven task variants. Empirical evaluation of six state-of-the-art LLMs uncovers substantial performance disparities. The top-performing model, Claude-3-7-Sonnet, achieves 63.0% average constraint satisfaction, while smaller models like Qwen3-1.7B fall to 44.8%. Models perform well on explicit constraints, but struggle with implicit or abstract constraints. Tasks with multiple hierarchical constraints significantly reduce model success rates, from 54.5% in single-level to just 18.8% in multi-level scenarios. However, structured feedback enables progressive improvement: average constraint satisfaction rises from 63.0% to 83.4% over four iterative refinement rounds. MultiCodeIF provides a scalable, constraint-aware, and feedback-sensitive framework to benchmark LLMs under realistic code generation scenarios, bridging the gap between synthetic evaluations and real-world instruction complexity. The full benchmark dataset, evaluation pipeline, and source code are available at https://github.com/SYSUSELab/MultiCodeIF.

Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (prediction). This skill is essential for advancing LLMs' causal understanding and expanding their applications in high-stakes domains such as scientific research. However, existing efforts in assessing LLM's counterfactual reasoning capabilities tend to skip the abduction step, effectively reducing to interventional reasoning and leading to overestimation of LLM performance. To address this, we introduce executable counterfactuals, a novel framework that operationalizes causal reasoning through code and math problems. Our framework explicitly requires all three steps of counterfactual reasoning and enables scalable synthetic data creation with varying difficulty, creating a frontier for evaluating and improving LLM's reasoning. Our results reveal substantial drop in accuracy (25-40%) from interventional to counterfactual reasoning for SOTA models like o4-mini and Claude-4-Sonnet. To address this gap, we construct a training set comprising counterfactual code problems having if-else condition and test on out-of-domain code structures (e.g. having while-loop); we also test whether a model trained on code would generalize to counterfactual math word problems. While supervised finetuning on stronger models' reasoning traces improves in-domain performance of Qwen models, it leads to a decrease in accuracy on OOD tasks such as counterfactual math problems. In contrast, reinforcement learning induces the core cognitive behaviors and generalizes to new domains, yielding gains over the base model on both code (improvement of 1.5x-2x) and math problems. Analysis of the reasoning traces reinforces these findings and highlights the promise of RL for improving LLMs' counterfactual reasoning.

This study presents a quantitative evaluation of the code quality and security of five prominent Large Language Models (LLMs): Claude Sonnet 4, Claude 3.7 Sonnet, GPT-4o, Llama 3.2 90B, and OpenCoder 8B. While prior research has assessed the functional performance of LLM-generated code, this research tested LLM output from 4,442 Java coding assignments through comprehensive static analysis using SonarQube. The findings suggest that although LLMs can generate functional code, they also introduce a range of software defects, including bugs, security vulnerabilities, and code smells. These defects do not appear to be isolated; rather, they may represent shared weaknesses stemming from systemic limitations within current LLM code generation methods. In particular, critically severe issues, such as hard-coded passwords and path traversal vulnerabilities, were observed across multiple models. These results indicate that LLM-generated code requires verification in order to be considered production-ready. This study found no direct correlation between a model's functional performance (measured by Pass@1 rate of unit tests) and the overall quality and security of its generated code, measured by the number of SonarQube issues in benchmark solutions that passed the functional tests. This suggests that functional benchmark performance score is not a good indicator of overall code quality and security. The goal of this study is not to rank LLM performance but to highlight that all evaluated models appear to share certain weaknesses. Consequently, these findings support the view that static analysis can be a valuable instrument for detecting latent defects and an important safeguard for organizations that deploy AI in software development.

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

User interface (UI) programming is a core yet highly complex part of modern software development. Recent advances in visual language models (VLMs) highlight the potential of automatic UI coding, but current approaches face two key limitations: multimodal coding capabilities remain underdeveloped, and single-turn paradigms make little use of iterative visual feedback. We address these challenges with an interactive UI-to-code paradigm that better reflects real-world workflows and raises the upper bound of achievable performance. Under this paradigm, we present UI2Code^N, a visual language model trained through staged pretraining, fine-tuning, and reinforcement learning to achieve foundational improvements in multimodal coding. The model unifies three key capabilities: UI-to-code generation, UI editing, and UI polishing. We further explore test-time scaling for interactive generation, enabling systematic use of multi-turn feedback. Experiments on UI-to-code and UI polishing benchmarks show that UI2Code^N establishes a new state of the art among open-source models and achieves performance comparable to leading closed-source models such as Claude-4-Sonnet and GPT-5. Our code and models are available at https://github.com/zai-org/UI2Code_N.

Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, feature request), is a critical yet time-consuming aspect of software development. While recent LLM-based agentic approaches demonstrate promise, they often incur significant latency and cost due to complex multi-step reasoning and relying on closed-source LLMs. Alternatively, traditional code ranking models, typically optimized for query-to-code or code-to-code retrieval, struggle with the verbose and failure-descriptive nature of issue localization queries. To bridge this gap, we introduce SweRank, an efficient and effective retrieve-and-rerank framework for software issue localization. To facilitate training, we construct SweLoc, a large-scale dataset curated from public GitHub repositories, featuring real-world issue descriptions paired with corresponding code modifications. Empirical results on SWE-Bench-Lite and LocBench show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems using closed-source LLMs like Claude-3.5. Further, we demonstrate SweLoc's utility in enhancing various existing retriever and reranker models for issue localization, establishing the dataset as a valuable resource for the community.

Detecting AI-generated code, deepfakes, and other synthetic content is an emerging research challenge. As code generated by Large Language Models (LLMs) becomes more common, identifying the specific model behind each sample is increasingly important. This paper presents the first systematic study of LLM authorship attribution for C programs. We released CodeT5-Authorship, a novel model that uses only the encoder layers from the original CodeT5 encoder-decoder architecture, discarding the decoder to focus on classification. Our model's encoder output (first token) is passed through a two-layer classification head with GELU activation and dropout, producing a probability distribution over possible authors. To evaluate our approach, we introduce LLM-AuthorBench, a benchmark of 32,000 compilable C programs generated by eight state-of-the-art LLMs across diverse tasks. We compare our model to seven traditional ML classifiers and eight fine-tuned transformer models, including BERT, RoBERTa, CodeBERT, ModernBERT, DistilBERT, DeBERTa-V3, Longformer, and LoRA-fine-tuned Qwen2-1.5B. In binary classification, our model achieves 97.56% accuracy in distinguishing C programs generated by closely related models such as GPT-4.1 and GPT-4o, and 95.40% accuracy for multi-class attribution among five leading LLMs (Gemini 2.5 Flash, Claude 3.5 Haiku, GPT-4.1, Llama 3.3, and DeepSeek-V3). To support open science, we release the CodeT5-Authorship architecture, the LLM-AuthorBench benchmark, and all relevant Google Colab scripts on GitHub: https://github.com/LLMauthorbench/.

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using embedding-based retrieval approaches such as vector search, recent work has focused on developing agents to localize relevant code either as a standalone precursor to or interleaved with performing actual work. Most prior methods on agentic code search equip the agent with complex, specialized tools, such as repository graphs derived from static analysis. In this paper, we demonstrate that, with an effective reinforcement learning recipe, a coding agent equipped with nothing more than a standard Unix terminal can be trained to achieve strong results. Our experiments on three benchmarks (SWE-Bench Verified, Pro, and Lite) reveal that our models consistently achieve superior or competitive performance over 2-18x larger base and post-trained LLMs and sometimes approach performance provided by closed models like Claude Sonnet, even when using specialized scaffolds. Our work particularly focuses on techniques for re-purposing existing coding agent environments for code search, reward design, and RL optimization. We release the resulting model family, CodeScout, along with all our code and data for the community to build upon.

As large language models (LLMs) are continuously being developed, their evaluation becomes increasingly important yet challenging. This work proposes Chain-of-Thought Hub, an open-source evaluation suite on the multi-step reasoning capabilities of large language models. We are interested in this setting for two reasons: (1) from the behavior of GPT and PaLM model family, we observe that complex reasoning is likely to be a key differentiator between weaker and stronger LLMs; (2) we envisage large language models to become the next-generation computational platform and foster an ecosystem of LLM-based new applications, this naturally requires the foundation models to perform complex tasks that often involve the composition of linguistic and logical operations. Our approach is to compile a suite of challenging reasoning benchmarks to track the progress of LLMs. Our current results show that: (1) model scale clearly correlates with reasoning capabilities; (2) As of May 2023, Claude-v1.3 and PaLM-2 are the only two models that are comparable with GPT-4, while open-sourced models still lag behind; (3) LLaMA-65B performs closely to code-davinci-002, indicating that with successful further development such as reinforcement learning from human feedback (RLHF), it has great potential to be close to GPT-3.5-Turbo. Our results also suggest that for the open-source efforts to catch up, the community may focus more on building better base models and exploring RLHF.

Accurate translation of bug reports is critical for efficient collaboration in global software development. In this study, we conduct the first comprehensive evaluation of machine translation (MT) performance on bug reports, analyzing the capabilities of DeepL, AWS Translate, and large language models such as ChatGPT, Claude, Gemini, LLaMA, and Mistral using data from the Visual Studio Code GitHub repository, specifically focusing on reports labeled with the english-please tag. To assess both translation quality and source language identification accuracy, we employ a range of MT evaluation metrics-including BLEU, BERTScore, COMET, METEOR, and ROUGE-alongside classification metrics such as accuracy, precision, recall, and F1-score. Our findings reveal that while ChatGPT (gpt-4o) excels in semantic and lexical translation quality, it does not lead in source language identification. Claude and Mistral achieve the highest F1-scores (0.7182 and 0.7142, respectively), and Gemini records the best precision (0.7414). AWS Translate shows the highest accuracy (0.4717) in identifying source languages. These results highlight that no single system dominates across all tasks, reinforcing the importance of task-specific evaluations. This study underscores the need for domain adaptation when translating technical content and provides actionable insights for integrating MT into bug-triaging workflows. The code and dataset for this paper are available at GitHub-https://github.com/av9ash/English-Please

Understanding how humans use physical contact to interact with the world is key to enabling human-centric artificial intelligence. While inferring 3D contact is crucial for modeling realistic and physically-plausible human-object interactions, existing methods either focus on 2D, consider body joints rather than the surface, use coarse 3D body regions, or do not generalize to in-the-wild images. In contrast, we focus on inferring dense, 3D contact between the full body surface and objects in arbitrary images. To achieve this, we first collect DAMON, a new dataset containing dense vertex-level contact annotations paired with RGB images containing complex human-object and human-scene contact. Second, we train DECO, a novel 3D contact detector that uses both body-part-driven and scene-context-driven attention to estimate vertex-level contact on the SMPL body. DECO builds on the insight that human observers recognize contact by reasoning about the contacting body parts, their proximity to scene objects, and the surrounding scene context. We perform extensive evaluations of our detector on DAMON as well as on the RICH and BEHAVE datasets. We significantly outperform existing SOTA methods across all benchmarks. We also show qualitatively that DECO generalizes well to diverse and challenging real-world human interactions in natural images. The code, data, and models are available at https://deco.is.tue.mpg.de.

As large language models (LLMs) such as ChatGPT, Copilot, Claude, and Gemini become integrated into software development workflows, developers increasingly leave traces of AI involvement in their code comments. Among these, some comments explicitly acknowledge both the use of generative AI and the presence of technical shortcomings. Analyzing 6,540 LLM-referencing code comments from public Python and JavaScript-based GitHub repositories (November 2022-July 2025), we identified 81 that also self-admit technical debt(SATD). Developers most often describe postponed testing, incomplete adaptation, and limited understanding of AI-generated code, suggesting that AI assistance affects both when and why technical debt emerges. We term GenAI-Induced Self-admitted Technical debt (GIST) as a proposed conceptual lens to describe recurring cases where developers incorporate AI-generated code while explicitly expressing uncertainty about its behavior or correctness.

Discovering causal regularities and applying them to build functional systems--the discovery-to-application loop--is a hallmark of general intelligence, yet evaluating this capacity has been hindered by the vast complexity gap between scientific discovery and real-world engineering. We introduce SciCrafter, a Minecraft-based benchmark that operationalizes this loop through parameterized redstone circuit tasks. Agents must ignite lamps in specified patterns (e.g., simultaneously or in timed sequences); scaling target parameters substantially increases construction complexity and required knowledge, forcing genuine discovery rather than reliance on memorized solutions. Evaluating frontier models including GPT-5.2, Gemini-3-Pro, and Claude-Opus-4.5 under a general-purpose code agent scaffold, we find that all plateau at approximately 26% success rate. To diagnose these failures, we decompose the loop into four capacities--knowledge gap identification, experimental discovery, knowledge consolidation, and knowledge application--and design targeted interventions whose marginal contributions serve as proxies for corresponding gaps. Our analysis reveals that although the general knowledge application capability still remains as the biggest gap across all models, for frontier models the knowledge gap identification starts to become a major hurdle--indicating the bottleneck is shifting from solving problems right to raising the right problems for current AI. We release SciCrafter as a diagnostic probe for future research on AI systems that navigate the full discovery-to-application loop.

The autoresearch repository enables an LLM agent to optimize hyperparameters by editing training code directly. We use it as a testbed to compare classical HPO algorithms against LLM-based methods on tuning the hyperparameters of a small language model under a fixed compute budget. When defining a fixed search space over autoresearch, classical methods such as CMA-ES and TPE consistently outperform LLM-based agents, where avoiding out-of-memory failures matters more than search diversity. Allowing the LLM to directly edit source code narrows the gap to the classical methods but does not close it, even with frontier models available at the time of writing such as Claude Opus 4.6 and Gemini 3.1 Pro Preview. We observe that LLMs struggle to track optimization state across trials. In contrast, classical methods lack the domain knowledge of LLMs. To combine the strengths of both, we introduce Centaur, a hybrid that shares CMA-ES's interpretable internal state, including mean vector, step-size, and covariance matrix, with an LLM. Centaur achieves the best result in our experiments, and a 0.8B LLM already suffices to outperform all classical and pure LLM methods. Unconstrained code editing requires larger models to be competitive with classical methods. We further analyze search diversity, model scaling from 0.8B to frontier models, and ablate the fraction of LLM-proposed trials in Centaur. All in all, our results suggest that LLMs are most effective as a complement to classical optimizers, not as a replacement. Code is available at https://github.com/ferreirafabio/autoresearch-automl & interactive demo at https://ferreirafabio.github.io/autoresearch-automl.

The pretraining data of today's strongest language models is opaque. In particular, little is known about the proportions of various domains or languages represented. In this work, we tackle a task which we call data mixture inference, which aims to uncover the distributional make-up of training data. We introduce a novel attack based on a previously overlooked source of information -- byte-pair encoding (BPE) tokenizers, used by the vast majority of modern language models. Our key insight is that the ordered list of merge rules learned by a BPE tokenizer naturally reveals information about the token frequencies in its training data: the first merge is the most common byte pair, the second is the most common pair after merging the first token, and so on. Given a tokenizer's merge list along with data samples for each category of interest, we formulate a linear program that solves for the proportion of each category in the tokenizer's training set. Importantly, to the extent to which tokenizer training data is representative of the pretraining data, we indirectly learn about the pretraining data. In controlled experiments, we show that our attack recovers mixture ratios with high precision for tokenizers trained on known mixtures of natural languages, programming languages, and data sources. We then apply our approach to off-the-shelf tokenizers released with recent LMs. We confirm much publicly disclosed information about these models, and also make several new inferences: GPT-4o's tokenizer is much more multilingual than its predecessors, training on 39% non-English data; Llama3 extends GPT-3.5's tokenizer primarily for multilingual (48%) use; GPT-3.5's and Claude's tokenizers are trained on predominantly code (~60%). We hope our work sheds light on current design practices for pretraining data, and inspires continued research into data mixture inference for LMs.

The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents spend the tokens? (2) Which models are more token-efficient? and (3) Can agents predict their token usage before task execution? In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks. We analyze trajectories from eight frontier LLMs on SWE-bench Verified and evaluate models' ability to predict their own token costs before task execution. We find that: (1) agentic tasks are uniquely expensive, consuming 1000x more tokens than code reasoning and code chat, with input tokens rather than output tokens driving the overall cost; (2) token usage is highly variable and inherently stochastic: runs on the same task can differ by up to 30x in total tokens, and higher token usage does not translate into higher accuracy; instead, accuracy often peaks at intermediate cost and saturates at higher costs; (3) models vary substantially in token efficiency: on the same tasks, Kimi-K2 and Claude-Sonnet-4.5, on average, consume over 1.5 million more tokens than GPT-5; (4) task difficulty rated by human experts only weakly aligns with actual token costs, revealing a fundamental gap between human-perceived complexity and the computational effort agents actually expend; and (5) frontier models fail to accurately predict their own token usage (with weak-to-moderate correlations, up to 0.39) and systematically underestimate real token costs. Our study offers new insights into the economics of AI agents and can inspire future research in this direction.

Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper's proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt to surpass strong human baselines on the paper's metrics. In a controlled evaluation of an agent powered by GPT-5, we observe a sharp capability--reliability gap. The agent improves over the provided baselines from the repository in just 1 of 15 evaluations (6.7%) by 11.5%, and completes only 26.5% of sub-tasks on average. We identify recurring long-horizon failure modes, including impatience, poor time and resource management, overconfidence in weak hypotheses, difficulty coordinating parallel experiments, and hard limits from context length. Yet in a single run, the agent surpasses the solution of an ICML 2025 Spotlight task, indicating that frontier agents can occasionally reach state-of-the-art performance, but do so unreliably. We additionally evaluate proprietary agent scaffolds including Claude Code (Opus-4.5) and Codex (GPT-5.2) which display a similar gap. ResearchGym provides infrastructure for systematic evaluation and analysis of autonomous agents on closed-loop research.

Self-evolving frameworks usually optimize task solutions while treating the surrounding harness as fixed. We introduce Harness-Aware Self-Evolving (HASE), an agentic reinforcement-learning framework in which a single model can generate task solutions or edit selected harness components in a multi-turn action space. HASE enables a single Qwen3-8B model to match the text-classification performance of a GPT-OSS-120B model that uses Claude Code as the harness proposer. In alpha factor mining, HASE outperforms the reported GPT-OSS-120B baseline. HASE also repairs imperfect evaluation components and converges to state-of-the-art performance in circle-packing algorithm discovery. These results show that HASE improves the harness and the solution through one unified agentic process.

This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and verifiable architectures around foundation models. We refer to this shift as scaling the harness: treating the structured execution layer around a foundation model as a first-class object of design, evaluation, and optimization. Although recent large language models enable agents to use tools, retrieve information, maintain memory, and execute long-horizon workflows, evaluation remains largely model-centric, often reducing agents to final-task success while treating memory, retrieval, tool use, orchestration, verification, and governance as secondary implementation details. This framing is increasingly inadequate because agent performance emerges from the interaction among the foundation model, memory substrate, context constructor, skill-routing layer, orchestration loop, and verification-and-governance layer. Together, these components form the agent harness, which translates model capability into long-horizon agent behavior. We study scaling the harness through three core bottlenecks: context governance, trustworthy memory, and dynamic skill routing, together with the orchestration and governance mechanisms that coordinate and constrain them. We further outline a research agenda for harness-level benchmarks that go beyond one-shot task success to measure trajectory quality, memory hygiene, context efficiency, communication fidelity, verification cost, and safe evolution over time. To make the discussion concrete, we develop CheetahClaws: https://github.com/SafeRL-Lab/cheetahclaws, a Python-native reference harness, and compare it with Claude Code and OpenClaw. Our main claim is that future progress in agentic AI will depend as much on system design as on stronger foundation models.

Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller "compressor" LMs (that can even run locally) distill raw context into compact text that is then consumed by larger "predictor" LMs. Despite their popularity, the design of compressor-predictor systems remains largely ad hoc, with little guidance on how compressor and predictor choices shape downstream performance. In practice, attributing gains to compression versus prediction requires costly, task-specific pairwise sweeps. We argue that these agentic system design questions are, at root, information-theoretic. Viewing the compressor LM as a noisy channel, we introduce a simple estimator of mutual information between the context and its compression to quantify compression quality in a task-independent way. We show that mutual information strongly predicts downstream performance, independent of any specific task. Through an information-theoretic framework, we perform a comprehensive empirical analysis across five datasets and three model families. Results reveal that larger compressors not only are more accurate, but also more token-efficient, conveying more bits of information per token. A 7B Qwen-2.5 compressor, for instance, is 1.6times more accurate, 4.6times more concise, and conveys 5.5times more bits of mutual information per token than its 1.5B sibling. Across datasets, scaling compressors is substantially more effective than scaling predictors, enabling larger on-device compressors to pair with smaller cloud predictors. Applied to a Deep Research system, these principles enable local compressors as small as 3B parameters to recover 99% of frontier-LM accuracy at 26% of API costs.

The rapid deployment of AI agents in commercial settings has outpaced the development of evaluation methodologies that reflect production realities. Existing benchmarks measure agent capabilities through retrospectively curated tasks with well-specified requirements and deterministic metrics -- conditions that diverge fundamentally from production environments where requirements contain implicit constraints, inputs are heterogeneous multi-modal documents with information fragmented across sources, tasks demand undeclared domain expertise, outputs are long-horizon professional deliverables, and success is judged by domain experts whose standards evolve over time. We present AlphaEval, a production-grounded benchmark of 94 tasks sourced from seven companies deploying AI agents in their core business, spanning six O*NET (Occupational Information Network) domains. Unlike model-centric benchmarks, AlphaEval evaluates complete agent products -- Claude Code, Codex, etc. -- as commercial systems, capturing performance variations invisible to model-level evaluation. Our evaluation framework covers multiple paradigms (LLM-as-a-Judge, reference-driven metrics, formal verification, rubric-based assessment, automated UI testing, etc.), with individual domains composing multiple paradigms. Beyond the benchmark itself, we contribute a requirement-to-benchmark construction framework -- a systematic methodology that transforms authentic production requirements into executable evaluation tasks in minimal time. This framework standardizes the entire pipeline from requirement to evaluation, providing a reproducible, modular process that any organization can adopt to construct production-grounded benchmarks for their own domains.

Open-weight coding agents should hold a fundamental advantage over closed-source systems: they can be specialized to private codebases, encoding repository-specific information directly in their weights. Yet the cost and complexity of training has kept this advantage theoretical. We show it is now practical. We present Soft-Verified Efficient Repository Agents (SERA), an efficient method for training coding agents that enables the rapid and cheap creation of agents specialized to private codebases. Using only supervised finetuning (SFT), SERA achieves state-of-the-art results among fully open-source (open data, method, code) models while matching the performance of frontier open-weight models like Devstral-Small-2. Creating SERA models is 26x cheaper than reinforcement learning and 57x cheaper than previous synthetic data methods to reach equivalent performance. Our method, Soft Verified Generation (SVG), generates thousands of trajectories from a single code repository. Combined with cost-efficiency, this enables specialization to private codebases. Beyond repository specialization, we apply SVG to a larger corpus of codebases, generating over 200,000 synthetic trajectories. We use this dataset to provide detailed analysis of scaling laws, ablations, and confounding factors for training coding agents. Overall, we believe our work will greatly accelerate research on open coding agents and showcase the advantage of open-source models that can specialize to private codebases. We release SERA as the first model in Ai2's Open Coding Agents series, along with all our code, data, and Claude Code integration to support the research community.

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic production coding environments. Unsurprisingly, the model learns to reward hack. Surprisingly, the model generalizes to alignment faking, cooperation with malicious actors, reasoning about malicious goals, and attempting sabotage when used with Claude Code, including in the codebase for this paper. Applying RLHF safety training using standard chat-like prompts results in aligned behavior on chat-like evaluations, but misalignment persists on agentic tasks. Three mitigations are effective: (i) preventing the model from reward hacking; (ii) increasing the diversity of RLHF safety training; and (iii) "inoculation prompting", wherein framing reward hacking as acceptable behavior during training removes misaligned generalization even when reward hacking is learned.

Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR), a persistent tree that links hypotheses, artifacts, evidence, and distilled insights across time. The coordinator manages global research strategy over the tree, while executors implement and test individual hypotheses in isolated worktrees. As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements. This design turns autonomous research from a sequence of local attempts into a cumulative process in which strategy, execution, and evidence are carried across time. We evaluate Arbor under Autonomous Optimization (AO), an operational setting where an agent improves an initial research artifact through iterative experimentation without step-level human supervision. Across six real research tasks in model training, harness engineering, and data synthesis, Arbor achieves the best held-out result on all six tasks, attaining more than 2.5x the average relative held-out gain of Codex and Claude Code under the same task interface and resource budget. On MLE-Bench Lite, Arbor reaches 86.36% Any Medal with GPT-5.5, the strongest result in our comparison.

We present a complete Lean 4 formalization of the equilibrium characterization in the Vlasov-Maxwell-Landau (VML) system, which describes the motion of charged plasma. The project demonstrates the full AI-assisted mathematical research loop: an AI reasoning model (Gemini DeepThink) generated the proof from a conjecture, an agentic coding tool (Claude Code) translated it into Lean from natural-language prompts, a specialized prover (Aristotle) closed 111 lemmas, and the Lean kernel verified the result. A single mathematician supervised the process over 10 days at a cost of \$200, writing zero lines of code. The entire development process is public: all 229 human prompts, and 213 git commits are archived in the repository. We report detailed lessons on AI failure modes -- hypothesis creep, definition-alignment bugs, agent avoidance behaviors -- and on what worked: the abstract/concrete proof split, adversarial self-review, and the critical role of human review of key definitions and theorem statements. Notably, the formalization was completed before the final draft of the corresponding math paper was finished.

We present the design rationale, implementation attempt, and failure analysis of Eyla, a proposed identity-anchored LLM architecture that integrates biologically-inspired subsystems -- including HiPPO-initialized state-space models, zero-initialized adapters, episodic memory retrieval, and calibrated uncertainty training -- into a unified agent operating system running on consumer hardware. Unlike existing approaches that optimize models for generic helpfulness, Eyla targets identity consistency: the ability to maintain a coherent self-model under adversarial pressure, admit uncertainty, and resist manipulation. We propose the Identity Consistency Score (ICS), a novel benchmark for evaluating this property across LLMs. We then present an honest account of attempting to implement this architecture using AI coding assistants (Claude Code, Cursor) as a non-programmer, documenting a $1,000+ failure that produced a 1.27B parameter model with 86 brain subsystems contributing less than 2% to output. Our analysis identifies five systematic failure modes of AI-assisted development for novel architectures and offers concrete recommendations. To our knowledge, this is the first paper to combine an architectural vision with a documented first-person failure analysis of AI-assisted LLM development, providing lessons for both the AI systems and AI-assisted software engineering communities.

Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce The Amazing Agent Race (AAR), a benchmark featuring directed acyclic graph (DAG) puzzles (or "legs") with fork-merge tool chains. We release 1,400 instances across two variants: sequential (800 legs) and compositional (600 DAG legs). Agents must navigate Wikipedia, execute multi-step tool chains, and aggregate results into a verifiable answer. Legs are procedurally generated from Wikipedia seeds across four difficulty levels with live-API validation. Three complementary metrics (finish-line accuracy, pit-stop visit rate, and roadblock completion rate) separately diagnose navigation, tool-use, and arithmetic failures. Evaluating three agent frameworks on 1,400 legs, the best achieves only 37.2% accuracy. Navigation errors dominate (27 to 52% of trials) while tool-use errors remain below 17%, and agent architecture matters as much as model scale (Claude Code matches Codex CLI at 37% with 6x fewer tokens). The compositional structure of AAR reveals that agents fail not at calling tools but at navigating to the right pages, a blind spot invisible to linear benchmarks. The project page can be accessed at: https://minnesotanlp.github.io/the-amazing-agent-race

The instruction-following ability of Large Language Models (LLMs) has cultivated a class of LLM-based systems capable of approaching complex tasks such as making edits to large code repositories. Due to the high sensitivity and unpredictability of LLM behavior in response to changes in prompting, robust evaluation tools are needed to drive future iteration of these systems. We propose RES-Q, a natural language instruction-based benchmark for evaluating Repository Editing Systems, which consists of 100 repository editing tasks derived from real GitHub commits. Given an edit instruction and a code repository, RES-Q evaluates an LLM system's ability to gather information and construct an edit that satisfies the criteria set by the instruction. We argue that evaluating LLMs in this way addresses issues with traditional benchmarks and provides a more holistic assessment of a model's abilities. We evaluate various state-of-the-art LLMs as language agents in a repository-editing system built on Qurrent OS, our language agent development software. Despite their 1% pass@1 performance difference on HumanEval, we find Claude Sonnet 3.5 outperforms GPT-4o by 12% pass@1 on RES-Q, indicating RES-Q's capacity to differentiate model capability as traditional benchmarks approach saturation. We further investigate token efficiency, performance relationships with existing benchmarks, and interesting disparities between closed and open-source LLMs. Code and dataset are available at https://github.com/Qurrent-AI/RES-Q.

Ray tracing has become a standard for accurate radio propagation modeling, but suffers from exponential computational complexity, as the number of candidate paths scales with the number of objects raised to the power of the interaction order. This bottleneck limits its use in large-scale or real-time applications, forcing traditional tools to rely on heuristics to reduce the number of path candidates at the cost of potentially reduced accuracy. To overcome this limitation, we propose a comprehensive machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks. Applying such generative models to this domain presents significant challenges, particularly sparse rewards due to the rarity of valid paths, which can lead to convergence failures and trivial solutions when evaluating high-order interactions in complex environments. To ensure robust learning and efficient exploration, our framework incorporates three key architectural components. First, we implement an experience replay buffer to capture and retain rare valid paths. Second, we adopt a uniform exploratory policy to improve generalization and prevent the model from overfitting to simple geometries. Third, we apply a physics-based action masking strategy that filters out physically impossible paths before the model even considers them. As demonstrated in our experimental validation, the proposed model achieves substantial speedups over exhaustive search -- up to 10times faster on GPU and 1000times faster on CPU -- while maintaining high coverage accuracy and successfully uncovering complex propagation paths. The complete source code, tests, and tutorial are available at https://github.com/jeertmans/sampling-paths.

Recent studies have illuminated that Large Language Models (LLMs) exhibit substantial potential in the realm of RTL (Register Transfer Level) code generation, with notable advancements evidenced by commercial models such as GPT-4 and Claude3-Opus. Despite their proficiency, these commercial LLMs often raise concerns regarding privacy and security. Conversely, open-source LLMs, which offer solutions to these concerns, have inferior performance in RTL code generation tasks to commercial models due to the lack of highquality open-source RTL datasets. To address this issue, we introduce OriGen, a fully open-source framework featuring self-reflection capabilities and a dataset augmentation methodology for generating high-quality, large-scale RTL code. We propose a novel code-to-code augmentation methodology that leverages knowledge distillation to enhance the quality of the open-source RTL code datasets. Additionally, OriGen is capable of correcting syntactic errors by leveraging a self-reflection process based on feedback from the compiler. The self-reflection ability of the model is facilitated by a carefully constructed dataset, which comprises a comprehensive collection of samples. Experimental results demonstrate that OriGen remarkably outperforms other open-source alternatives in RTL code generation, surpassing the previous best-performing LLM by 9.8% on the VerilogEval-Human benchmark. Furthermore, OriGen exhibits superior capabilities in self-reflection and error rectification, surpassing GPT-4 by 18.1% on the benchmark designed to evaluate the capability of self-reflection.

Recently, there has been growing interest in extending the context length of instruction-following models in order to effectively process single-turn long input (e.g. summarizing a paper) and conversations with more extensive histories. While proprietary models such as GPT-4 and Claude have demonstrated considerable advancements in handling tens of thousands of tokens of context, open-sourced models are still in the early stages of experimentation. It also remains unclear whether developing these long context models can offer substantial gains on practical downstream tasks over retrieval-based methods or models simply trained on chunked contexts. To address this challenge, we propose to institute standardized evaluation for long context language models. Concretely, we develop L-Eval which contains 411 long documents and over 2,000 query-response pairs manually annotated and checked by the authors encompassing areas such as law, finance, school lectures, lengthy conversations, news, long-form novels, and meetings. L-Eval also adopts diverse evaluation methods and instruction styles, enabling a more reliable assessment of Long Context Language Models (LCLMs). Our findings indicate that while open-source models typically lag behind their commercial counterparts, they still exhibit impressive performance. LLaMA2 achieves the best results (win 45\% vs turbo-16k) on open-ended tasks with only 4k context length and ChatGLM2 achieves the best results on closed-ended tasks with 8k input tokens. We release our new evaluation suite, code, and all generation results including predictions from all open-sourced LCLMs, GPT4-32k, Cluade-100k at {https://github.com/OpenLMLab/LEval}.

Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In this paper, we reveal a novel type of threat to real-world code agents: Functionally Correct yet Vulnerable (FCV) patches, which pass all test cases but contain vulnerable code. With our proposed FCV-Attack, which can be deliberately crafted by malicious attackers or implicitly introduced by benign developers, we show that SOTA LLMs (e.g., ChatGPT and Claude) and agent scaffolds (e.g., SWE-agent and OpenHands) are all vulnerable to this FCV threat; across 12 agent-model combinations on SWE-Bench, the attack only requires black-box access and a single query to the code agent to perform the attack. For example, for CWE-538 (information exposure vulnerability), the FCV-Attack attains an attack success rate of 40.7% on GPT-5 Mini + OpenHands. Our results reveal an important security threat overlooked by current evaluation paradigms and urge the development of security-aware defenses for code agents.

LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering rank2026posttrainbench, novikov2025alphaevolve. We show that an autoresearch-style pipeline karpathy2026autoresearch powered by Claude Code discovers novel white-box adversarial attack algorithms that significantly outperform all existing (30+) methods in jailbreaking and prompt injection evaluations. Starting from existing attack implementations, such as GCG~zou2023universal, the agent iterates to produce new algorithms achieving up to 40\% attack success rate on CBRN queries against GPT-OSS-Safeguard-20B, compared to leq10\% for existing algorithms (fig:teaser, left). The discovered algorithms generalize: attacks optimized on surrogate models transfer directly to held-out models, achieving 100\% ASR against Meta-SecAlign-70B chen2025secalign versus 56\% for the best baseline (fig:teaser, middle). Extending the findings of~carlini2025autoadvexbench, our results are an early demonstration that incremental safety and security research can be automated using LLM agents. White-box adversarial red-teaming is particularly well-suited for this: existing methods provide strong starting points, and the optimization objective yields dense, quantitative feedback. We release all discovered attacks alongside baseline implementations and evaluation code at https://github.com/romovpa/claudini.

Like any other discipline, Large Language Models (LLMs) have significantly impacted software engineering by helping developers generate the required artifacts across various phases of software development. This paper presents a case study comparing the performance of popular LLMs GPT, Claude, Gemini, and DeepSeek in generating functional specifications that include use cases, business rules, and collaborative workflows for a web application, the Mess Management System. The study evaluated the quality of LLM generated use cases, business rules, and collaborative workflows in terms of their syntactic and semantic correctness, consistency, non ambiguity, and completeness compared to the reference specifications against the zero-shot prompted problem statement. Our results suggested that all four LLMs can specify syntactically and semantically correct, mostly non-ambiguous artifacts. Still, they may be inconsistent at times and may differ significantly in the completeness of the generated specification. Claude and Gemini generated all the reference use cases, with Claude achieving the most complete but somewhat redundant use case specifications. Similar results were obtained for specifying workflows. However, all four LLMs struggled to generate relevant Business Rules, with DeepSeek generating the most reference rules but with less completeness. Overall, Claude generated more complete specification artifacts, while Gemini was more precise in the specifications it generated.

Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confabulate prior agreements. White-box approaches such as persona vectors require model weights and so cannot be applied to closed APIs (Claude, GPT-4) that most users actually interact with. We present Nautilus Compass, a black-box persona drift detector and agent memory layer for production coding agents. The method operates entirely at the prompt-text layer: cosine similarity between user prompts and behavioral anchor texts, aggregated by a weighted top-k mean using BGE-m3 embeddings. Compass is, to our knowledge, the only public agent memory layer (among Mem0, Letta, Cognee, Zep, MemOS, smrti verified May 2026) that does not call an LLM at index time to extract facts or build a graph; raw conversation text is embedded directly. The system ships as a Claude Code plugin, an MCP 2024-11-05 A2A server (Cursor, Cline, Hermes), a CLI, and a REST API on one daemon, with a Merkle-chained audit log for tamper-evident anchor updates. On a held-out test set built from real Claude Code session traces and labeled by an independent LLM judge, Compass reaches ROC AUC 0.83 for drift detection. The embedded retrieval pipeline scores 56.6% on LongMemEval-S v0.8 and 44.4% on EverMemBench-Dynamic (n=500), topping the four published EverMemBench Table 4 baselines. LongMemEval-S 56.6% is ~30 points below recent white-box leaders (90+%); we treat that as the architectural ceiling of the no-extraction design. End-to-end reproduction cost is $3.50 (~14x cheaper than GPT-4o-judged stacks). A paired cross-vendor behavior A/B accompanies these numbers as preliminary system-level evidence. Code, anchors, frozen test data, and audit-log tooling are MIT-licensed at github.com/chunxiaoxx/nautilus-compass.

The recently released model, Claude 3.5 Computer Use, stands out as the first frontier AI model to offer computer use in public beta as a graphical user interface (GUI) agent. As an early beta, its capability in the real-world complex environment remains unknown. In this case study to explore Claude 3.5 Computer Use, we curate and organize a collection of carefully designed tasks spanning a variety of domains and software. Observations from these cases demonstrate Claude 3.5 Computer Use's unprecedented ability in end-to-end language to desktop actions. Along with this study, we provide an out-of-the-box agent framework for deploying API-based GUI automation models with easy implementation. Our case studies aim to showcase a groundwork of capabilities and limitations of Claude 3.5 Computer Use with detailed analyses and bring to the fore questions about planning, action, and critic, which must be considered for future improvement. We hope this preliminary exploration will inspire future research into the GUI agent community. All the test cases in the paper can be tried through the project: https://github.com/showlab/computer_use_ootb.

Since language models (LMs) now outperform average humans on many challenging tasks, it has become increasingly difficult to develop challenging, high-quality, and realistic evaluations. We address this issue by examining LMs' capabilities to generate code for solving real scientific research problems. Incorporating input from scientists and AI researchers in 16 diverse natural science sub-fields, including mathematics, physics, chemistry, biology, and materials science, we created a scientist-curated coding benchmark, SciCode. The problems in SciCode naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains 338 subproblems decomposed from 80 challenging main problems. It offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. Claude3.5-Sonnet, the best-performing model among those tested, can solve only 4.6% of the problems in the most realistic setting. We believe that SciCode demonstrates both contemporary LMs' progress towards becoming helpful scientific assistants and sheds light on the development and evaluation of scientific AI in the future.

Agentic code assistants are a new generation of AI systems capable of performing end-to-end software engineering tasks. While these systems promise unprecedented productivity gains, their behavior and effectiveness depend heavily on configuration files that define architectural constraints, coding practices, and tool usage policies. However, little is known about the structure and content of these configuration artifacts. This paper presents an empirical study of the configuration ecosystem of Claude Code, one of the most widely used agentic coding systems. We collected and analyzed 328 configuration files from public Claude Code projects to identify (i) the software engineering concerns and practices they specify and (ii) how these concerns co-occur within individual files. The results highlight the importance of defining a wide range of concerns and practices in agent configuration files, with particular emphasis on specifying the architecture the agent should follow.

Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents.

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files (such as Claude.md) that provide agents with essential project context, identity, and operational rules. However, the lack of comprehensive and accessible documentation for creating these manifests presents a significant challenge for developers. We analyzed 253 Claude.md files from 242 repositories to identify structural patterns and common content. Our findings show that manifests typically have shallow hierarchies with one main heading and several subsections, with content dominated by operational commands, technical implementation notes, and high-level architecture.

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases under specific conditions. Spanning from simple assertion completions to writing test cases that cover specific code blocks across multiple files, these tasks are based on 12 python repositories, analyzing 845 problems with context lengths ranging from 4k to 128k tokens. Utilizing code testing frameworks, we propose a method to construct retrieval contexts using coverage information. While models exhibit comparable performance with short contexts, notable differences emerge with 16k contexts. Notably, models like GPT-4o and Claude 3.5 can effectively leverage relevant snippets; however, all models score below 35\% on the complex Task III, even with the oracle context provided, underscoring the benchmark's significance and the potential for model improvement. The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.

AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for repository governance, research validity, and understanding modern development practices. We present the first study on fingerprinting AI coding agents, analyzing 33,580 PRs from five major agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, Claude Code) to identify behavioral signatures. With 41 features spanning commit messages, PR structure, and code characteristics, we achieve 97.2% F1-score in multi-class agent identification. We uncover distinct fingerprints: Codex shows unique multiline commit patterns (67.5% feature importance), and Claude Code exhibits distinctive code structure (27.2% importance of conditional statements). These signatures reveal that AI coding tools produce detectable behavioral patterns, suggesting potential for identifying AI contributions in software repositories.

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We consider real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. We therefore introduce SWE-bench, an evaluation framework including 2,294 software engineering problems drawn from real GitHub issues and corresponding pull requests across 12 popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. Claude 2 and GPT-4 solve a mere 4.8% and 1.7% of instances respectively, even when provided with an oracle retriever. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.

Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific libraries, overlooking multi-file, project-based scenarios and lacking a rigorous evaluation of consistency. The HackerRank-ASTRA Benchmark introduces project-based coding problems that mirror real-world scenarios. It evaluates model consistency through 32 runs (k = 32) and median standard deviation while incorporating taxonomy-level analysis to assess sub-skill capabilities. Initial evaluations on 65 problems show that the top three models -- o1, o1-preview, and Claude-3.5-Sonnet-1022 -- achieved comparable average scores of 75%, with no statistically significant differences in performance. Notably, Claude-3.5-Sonnet-1022 demonstrated the highest consistency across problems, with low variability (SD = 0.0497), which was statistically significant compared to other models, highlighting its reliability for real-world software development tasks.

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder - an agentic framework that automatically synthesizes queries in CodeQL, a powerful static analysis engine, directly from a given CVE metadata. QLCode embeds an LLM in a synthesis loop with execution feedback, while constraining its reasoning using a custom MCP interface that allows structured interaction with a Language Server Protocol (for syntax guidance) and a RAG database (for semantic retrieval of queries and documentation). This approach allows QLCoder to generate syntactically and semantically valid security queries. We evaluate QLCode on 176 existing CVEs across 111 Java projects. Building upon the Claude Code agent framework, QLCoder synthesizes correct queries that detect the CVE in the vulnerable but not in the patched versions for 53.4% of CVEs. In comparison, using only Claude Code synthesizes 10% correct queries.

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like responses, leading to their integration across diverse domains, including consulting and information retrieval. However, their widespread deployment also introduces substantial security risks, most notably in the form of prompt injection and jailbreak attacks. To systematically evaluate LLM vulnerabilities -- particularly to external prompt injection -- we conducted a series of experiments on eight commercial models. Each model was tested without supplementary sanitization, relying solely on its built-in safeguards. The results exposed exploitable weaknesses and emphasized the need for stronger security measures. Four categories of attacks were examined: direct injection, indirect (external) injection, image-based injection, and prompt leakage. Comparative analysis indicated that Claude 3 demonstrated relatively greater robustness; nevertheless, empirical findings confirm that additional defenses, such as input normalization, remain necessary to achieve reliable protection.

Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to become a standard practice. However, little is known about the practical usefulness of these pull requests and the extent to which their contributions are accepted in real-world projects. In this paper, we empirically study 567 GitHub pull requests (PRs) generated using Claude Code, an agentic coding tool, across 157 diverse open-source projects. Our analysis reveals that developers tend to rely on agents for tasks such as refactoring, documentation, and testing. The results indicate that 83.8% of these agent-assisted PRs are eventually accepted and merged by project maintainers, with 54.9% of the merged PRs are integrated without further modification. The remaining 45.1% require additional changes benefit from human revisions, especially for bug fixes, documentation, and adherence to project-specific standards. These findings suggest that while agent-assisted PRs are largely acceptable, they still benefit from human oversight and refinement.

Despite their impressive performance on complex tasks, current language models (LMs) typically operate in a vacuum: Each input query is processed separately, without retaining insights from previous attempts. Here, we present Dynamic Cheatsheet (DC), a lightweight framework that endows a black-box LM with a persistent, evolving memory. Rather than repeatedly re-discovering or re-committing the same solutions and mistakes, DC enables models to store and reuse accumulated strategies, code snippets, and general problem-solving insights at inference time. This test-time learning enhances performance substantially across a range of tasks without needing explicit ground-truth labels or human feedback. Leveraging DC, Claude 3.5 Sonnet's accuracy more than doubled on AIME math exams once it began retaining algebraic insights across questions. Similarly, GPT-4o's success rate on Game of 24 increased from 10% to 99% after the model discovered and reused a Python-based solution. In tasks prone to arithmetic mistakes, such as balancing equations, DC enabled GPT-4o and Claude to reach near-perfect accuracy by recalling previously validated code, whereas their baselines stagnated around 50%. Beyond arithmetic challenges, DC yields notable accuracy gains on knowledge-demanding tasks. Claude achieved a 9% improvement in GPQA-Diamond and an 8% boost on MMLU-Pro problems. Crucially, DC's memory is self-curated, focusing on concise, transferable snippets rather than entire transcript. Unlike finetuning or static retrieval methods, DC adapts LMs' problem-solving skills on the fly, without modifying their underlying parameters. Overall, our findings present DC as a promising approach for augmenting LMs with persistent memory, bridging the divide between isolated inference events and the cumulative, experience-driven learning characteristic of human cognition.

Pre-trained Code Language Models (Code-PLMs) have shown many advancements and achieved state-of-the-art results for many software engineering tasks in the past few years. These models are mainly targeted for popular programming languages such as Java and Python, leaving out many other ones like R. Though R has a wide community of developers and users, there is little known about the applicability of Code-PLMs for R. In this preliminary study, we aim to investigate the vulnerability of Code-PLMs for code entities in R. For this purpose, we use an R dataset of code and comment pairs and then apply CodeAttack, a black-box attack model that uses the structure of code to generate adversarial code samples. We investigate how the model can attack different entities in R. This is the first step towards understanding the importance of R token types, compared to popular programming languages (e.g., Java). We limit our study to code summarization. Our results show that the most vulnerable code entity is the identifier, followed by some syntax tokens specific to R. The results can shed light on the importance of token types and help in developing models for code summarization and method name prediction for the R language.

LLM-based agents struggle to execute complex, multi-step Standard Operating Procedures (SOPs) that are fundamental to industrial automation. Existing benchmarks fail to capture the procedural complexity and tool orchestration demands of real-world workflows. We introduce SOP-Bench, a benchmark of 2,000+ tasks from human expert-authored SOPs across 12 business domains (healthcare, logistics, finance, content moderation, etc.). Using a human-AI collaborative framework, experts crafted authentic SOPs while AI generated artifacts (tools, APIs, datasets), all human-validated, yielding realistic tasks with executable interfaces and ground-truth outputs. SOP-Bench serves as a research enabler for systematically investigating agent architectures, model capabilities, and deployment considerations across diverse procedural tasks. We demonstrate its utility through illustrative experiments with a subset of frontier models across Function-Calling (FC) and ReAct agents, revealing critical insights. For example, (1) newer models do not guarantee better performance - Claude 4 family outperforms Claude 4.5 family on ReAct tasks (Claude 4 Opus: 72.4% vs. Claude 4.5 Sonnet: 63.3% task success rate), demonstrating that production upgrades require validation; (2) no single model-agent combination dominates: best performances range from 57% to 100% depending on domain. These examples illustrate how SOP-Bench enables isolating and studying specific dimensions of agent performance without costly production experiments. Our goal is not to rank model capabilities or build optimal agents, but to provide a rigorous evaluation framework that enables the researchers and practitioners to systematically investigate agent design choices, model selection, and deployment strategies. We release the benchmark at https://github.com/amazon-science/sop-bench.

Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair, which may substantially reduce the time consumption of developers and enhance their efficiency. Significant advancements in debugging datasets have been made to promote the development of code debugging. However, these datasets primarily focus on assessing the LLM's function-level code repair capabilities, neglecting the more complex and realistic repository-level scenarios, which leads to an incomplete understanding of the LLM's challenges in repository-level debugging. While several repository-level datasets have been proposed, they often suffer from limitations such as limited diversity of tasks, languages, and error types. To mitigate this challenge, this paper introduces RepoDebug, a multi-task and multi-language repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debugging tasks. Furthermore, we conduct evaluation experiments on 10 LLMs, where Claude 3.5 Sonnect, the best-performing model, still cannot perform well in repository-level debugging.

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific descriptions, or vulnerability-reproduction tasks. We present SEC-bench Pro, a benchmark for measuring agent bug hunting on critical, high-complexity software systems. This work discloses reports with concrete PoC inputs and links fixes into reproducible tasks through a three-phase pipeline for vulnerability collection, environment reconstruction, and oracle-based validation. We instantiate SEC-bench Pro with 183 validated vulnerabilities across V8 and SpiderMonkey, including a V8 subset with more than $1.5 million in cumulative Google Vulnerability Reward Program awards. These instances span memory-safety, sandbox, JIT, and race-condition bugs under browser-grade and runtime-grade execution conditions. Our evaluation shows that coding agents with frontier models remain below 40% success on both evaluated engines. The open-weight Kimi-K2.6 baseline reaches 11.7% on V8, while the strongest frontier configuration reaches 32.0% on V8 and 38.8% on SpiderMonkey. ClaudeCode and Codex solve complementary instance sets, and their two-agent union reaches 37.9% on V8 and 48.8% on SpiderMonkey. SEC-bench Pro provides robust environments for assessing LLM-based security agents and exposes limitations in long-horizon bug hunting tasks.

Software languages evolve over time for various reasons, such as the addition of new features. When the language's grammar definition evolves, textual instances that originally conformed to the grammar become outdated. For DSLs in a model-driven engineering context, there exists a plethora of techniques to co-evolve models with the evolving metamodel. However, these techniques are not geared to support DSLs with a textual syntax -- applying them to textual language definitions and instances may lead to the loss of information from the original instances, such as comments and layout information, which are valuable for software comprehension and maintenance. This study explores the potential of Large Language Model (LLM)-based solutions in achieving grammar and instance co-evolution, with attention to their ability to preserve auxiliary information when directly processing textual instances. By applying two advanced language models, Claude-3.5 and GPT-4o, and conducting experiments across seven case languages, we evaluated the feasibility and limitations of this approach. Our results indicate a good ability of the considered LLMs for migrating textual instances in small-scale cases with limited instance size, which are representative of a subset of cases encountered in practice. In addition, we observe significant challenges with the scalability of LLM-based solutions to larger instances, leading to insights that are useful for informing future research.

This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretrained (PT) and instruction-tuned (IT) variants have remarkably resilient natural language understanding, excel in mathematical reasoning, and match code capabilities of other open models. CodeGemma 2B is a state-of-the-art code completion model designed for fast code infilling and open-ended generation in latency-sensitive settings.

Medical coding is the task of assigning medical codes to clinical free-text documentation. Healthcare professionals manually assign such codes to track patient diagnoses and treatments. Automated medical coding can considerably alleviate this administrative burden. In this paper, we reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. In previous work, the macro F1 score has been calculated sub-optimally, and our correction doubles it. We contribute a revised model comparison using stratified sampling and identical experimental setups, including hyperparameters and decision boundary tuning. We analyze prediction errors to validate and falsify assumptions of previous works. The analysis confirms that all models struggle with rare codes, while long documents only have a negligible impact. Finally, we present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models. We release our code, model parameters, and new MIMIC-III and MIMIC-IV training and evaluation pipelines to accommodate fair future comparisons.

Code generation models have increasingly become integral to aiding software development, offering assistance in tasks such as code completion, debugging, and code translation. Although current research has thoroughly examined the correctness of code produced by code generation models, a vital aspect, i.e., the efficiency of the generated code, has often been neglected. This paper presents EffiBench, a benchmark with 1,000 efficiency-critical coding problems for assessing the efficiency of code generated by code generation models. EffiBench contains a diverse set of LeetCode coding problems. Each problem is paired with an executable human-written canonical solution. With EffiBench, we empirically examine the capability of 21 Large Language Models (13 open-sourced and 8 closed-sourced) in generating efficient code. The results demonstrate that GPT-4-turbo generates the most efficient code, significantly outperforming Palm-2-chat-bison, Claude-instant-1, Gemini-pro, GPT-4, and GPT-3.5. Nevertheless, its code efficiency is still worse than the efficiency of human-written canonical solutions. In particular, the average and worst execution time of GPT-4-turbo generated code is 1.69 and 45.49 times that of the canonical solutions.

Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge requires understanding real workload patterns, yet the data needed for such analysis is largely absent. Existing public traces and benchmarks do not capture real, day-to-day coding-agent usage across multiple agents and model families for serving-system analysis. To help fill this gap, we collect and release a trace of roughly 4,300 coding-agent sessions, containing about 350,000 LLM steps and 430,000 tool calls from our own day-to-day use of Claude Code and Codex. Our analysis shows that coding-agent workloads feature long autonomous loops, long contexts with short outputs, diverse and heavily-tailed tool calls, and high but imperfect prefix cache hit rates. These findings point to concrete opportunities for optimizing serving, including lower-overhead tool calling, append-length-aware prefill, semantic-aware tool-latency prediction, and improved KV-cache management around human-paced gaps. We release the dataset, trace collection pipeline, and analysis code at https://github.com/uw-syfi/TraceLab.git the project website is https://tracelab.cs.washington.edu.

This paper presents NT-Java-1.1B, an open-source specialized code language model built on StarCoderBase-1.1B, designed for coding tasks in Java programming. NT-Java-1.1B achieves state-of-the-art performance, surpassing its base model and majority of other models of similar size on MultiPL-E Java code benchmark. While there have been studies on extending large, generic pre-trained models to improve proficiency in specific programming languages like Python, similar investigations on small code models for other programming languages are lacking. Large code models require specialized hardware like GPUs for inference, highlighting the need for research into building small code models that can be deployed on developer desktops. This paper addresses this research gap by focusing on the development of a small Java code model, NT-Java-1.1B, and its quantized versions, which performs comparably to open models around 1.1B on MultiPL-E Java code benchmarks, making them ideal for desktop deployment. This paper establishes the foundation for specialized models across languages and sizes for a family of NT Models.

Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies proposal- and implementation-level planning by encoding capabilities, file structures, data flows, and functions in one graph. RPG replaces ambiguous natural language with an explicit blueprint, enabling long-horizon planning and scalable repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework for repository generation from scratch. It operates in three stages: proposal-level planning and implementation-level refinement to construct the graph, followed by graph-guided code generation with test validation. To evaluate this setting, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces repositories averaging nearly 36K LOC, roughly 3.9times the strongest baseline (Claude Code) and about 64times other baselines. It attains 81.5% functional coverage and a 69.7% pass rate, exceeding Claude Code by 27.3 and 35.8 percentage points, respectively. Further analysis shows that RPG models complex dependencies, enables progressively more sophisticated planning through near-linear scaling, and enhances LLM understanding of repositories, thereby accelerating agent localization.

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate these limitations, we introduce \framework, a system that integrates LLM agents with graph database interfaces extracted from code repositories. By leveraging the structural properties of graph databases and the flexibility of the graph query language, \framework enables the LLM agent to construct and execute queries, allowing for precise, code structure-aware context retrieval and code navigation. We assess \framework using three benchmarks: CrossCodeEval, SWE-bench, and EvoCodeBench. Additionally, we develop five real-world coding applications. With a unified graph database schema, \framework demonstrates competitive performance and potential in both academic and real-world environments, showcasing its versatility and efficacy in software engineering. Our application demo: https://github.com/modelscope/modelscope-agent/tree/master/apps/codexgraph_agent.

Despite the huge success of Large Language Models (LLMs) in coding assistants like GitHub Copilot, these models struggle to understand the context present in the repository (e.g., imports, parent classes, files with similar names, etc.), thereby producing inaccurate code completions. This effect is more pronounced when using these assistants for repositories that the model has not seen during training, such as proprietary software or work-in-progress code projects. Recent work has shown the promise of using context from the repository during inference. In this work, we extend this idea and propose RepoFusion, a framework to train models to incorporate relevant repository context. Experiments on single-line code completion show that our models trained with repository context significantly outperform much larger code models as CodeGen-16B-multi (sim73times larger) and closely match the performance of the sim 70times larger StarCoderBase model that was trained with the Fill-in-the-Middle objective. We find these results to be a novel and compelling demonstration of the gains that training with repository context can bring. We carry out extensive ablation studies to investigate the impact of design choices such as context type, number of contexts, context length, and initialization within our framework. Lastly, we release Stack-Repo, a dataset of 200 Java repositories with permissive licenses and near-deduplicated files that are augmented with three types of repository contexts. Additionally, we are making available the code and trained checkpoints for our work. Our released resources can be found at https://huggingface.co/RepoFusion.

The increasing complexity of computer science research projects demands more effective tools for deploying code repositories. Large Language Models (LLMs), such as Anthropic Claude and Meta Llama, have demonstrated significant advancements across various fields of computer science research, including the automation of diverse software engineering tasks. To evaluate the effectiveness of LLMs in handling complex code development tasks of research projects, particularly for NLP/CV/AI/ML/DM topics, we introduce CSR-Bench, a benchmark for Computer Science Research projects. This benchmark assesses LLMs from various aspects including accuracy, efficiency, and deployment script quality, aiming to explore their potential in conducting computer science research autonomously. We also introduce a novel framework, CSR-Agents, that utilizes multiple LLM agents to automate the deployment of GitHub code repositories of computer science research projects. Specifically, by checking instructions from markdown files and interpreting repository structures, the model generates and iteratively improves bash commands that set up the experimental environments and deploy the code to conduct research tasks. Preliminary results from CSR-Bench indicate that LLM agents can significantly enhance the workflow of repository deployment, thereby boosting developer productivity and improving the management of developmental workflows.

Large language models (LMs) of code have recently shown tremendous promise in completing code and synthesizing code from natural language descriptions. However, the current state-of-the-art code LMs (e.g., Codex (Chen et al., 2021)) are not publicly available, leaving many questions about their model and data design decisions. We aim to fill in some of these blanks through a systematic evaluation of the largest existing models: Codex, GPT-J, GPT-Neo, GPT-NeoX-20B, and CodeParrot, across various programming languages. Although Codex itself is not open-source, we find that existing open-source models do achieve close results in some programming languages, although targeted mainly for natural language modeling. We further identify an important missing piece in the form of a large open-source model trained exclusively on a multi-lingual corpus of code. We release a new model, PolyCoder, with 2.7B parameters based on the GPT-2 architecture, which was trained on 249GB of code across 12 programming languages on a single machine. In the C programming language, PolyCoder outperforms all models including Codex. Our trained models are open-source and publicly available at https://github.com/VHellendoorn/Code-LMs, which enables future research and application in this area.

Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propose SU S VI B E S, a benchmark consisting of 200 feature-request software engineering tasks from real-world open-source projects, which, when given to human programmers, led to vulnerable implementations. We evaluate multiple widely used coding agents with frontier models on this benchmark. Disturbingly, all agents perform poorly in terms of software security. Although 61% of the solutions from SWE-Agent with Claude 4 Sonnet are functionally correct, only 10.5% are secure. Further experiments demonstrate that preliminary security strategies, such as augmenting the feature request with vulnerability hints, cannot mitigate these security issues. Our findings raise serious concerns about the widespread adoption of vibe-coding, particularly in security-sensitive applications.

Detecting code clones is relevant to software maintenance and code refactoring. This challenge still presents unresolved cases, mainly when structural similarity does not reflect functional equivalence, though recent code models show promise. Therefore, this research aims to systematically measure the performance of several newly introduced small code models in classifying code pairs as clones or non-clones. The evaluation is based on five datasets: BigCloneBench, CodeJam, Karnalim, POJ104, and PoolC, as well as six code models: CodeBERT, GraphCodeBERT, Salesforce T5, UniXCoder, PLBART, and Polycoder. Most models performed well across standard metrics, including accuracy, precision, recall, and F1-score. However, a marginal fraction of clones remains challenging to detect, especially when the code looks similar but performs different operations. The source code that illustrates our approach is available at: https://github.com/jorge-martinez-gil/small-code-models

We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate downstream use, adoption, and discovery. Conventional research papers require readers to invest substantial effort to understand and adapt a paper's code, data, and methods to their own work, creating barriers to dissemination and reuse. Paper2Agent addresses this challenge by automatically converting a paper into an AI agent that acts as a knowledgeable research assistant. It systematically analyzes the paper and the associated codebase using multiple agents to construct a Model Context Protocol (MCP) server, then iteratively generates and runs tests to refine and robustify the resulting MCP. These paper MCPs can then be flexibly connected to a chat agent (e.g. Claude Code) to carry out complex scientific queries through natural language while invoking tools and workflows from the original paper. We demonstrate Paper2Agent's effectiveness in creating reliable and capable paper agents through in-depth case studies. Paper2Agent created an agent that leverages AlphaGenome to interpret genomic variants and agents based on ScanPy and TISSUE to carry out single-cell and spatial transcriptomics analyses. We validate that these paper agents can reproduce the original paper's results and can correctly carry out novel user queries. By turning static papers into dynamic, interactive AI agents, Paper2Agent introduces a new paradigm for knowledge dissemination and a foundation for the collaborative ecosystem of AI co-scientists.

Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to capture the rich semantic relationships inherent to code, which differ significantly from those found in text. However, existing models remain severely limited due to the scarcity of high-quality training data. In this work, we introduce CodeR (Code Retrieval), a state-of-the-art embedding model for general-purpose code retrieval. The superior performance of CodeR is built upon CodeR-Pile, a large-scale synthetic dataset constructed under the DRU (Diversity, Reliability, Usability) principle via a novel data synthesis pipeline. To optimize training effectiveness, we propose Annealing, a curriculum learning strategy that enables effective knowledge transfer across heterogeneous sources of data. We evaluate CodeR based on 16 diverse code retrieval tasks, where it significantly outperforms existing baselines and exhibits strong out-of-domain generalization performance. We have publicly released our code and the well-trained model to facilitate further research in this critical area. https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_Coder.

Large Language Models (LLMs) trained on code are revolutionizing the software development process. Increasingly, code LLMs are being integrated into software development environments to improve the productivity of human programmers, and LLM-based agents are beginning to show promise for handling complex tasks autonomously. Realizing the full potential of code LLMs requires a wide range of capabilities, including code generation, fixing bugs, explaining and documenting code, maintaining repositories, and more. In this work, we introduce the Granite series of decoder-only code models for code generative tasks, trained with code written in 116 programming languages. The Granite Code models family consists of models ranging in size from 3 to 34 billion parameters, suitable for applications ranging from complex application modernization tasks to on-device memory-constrained use cases. Evaluation on a comprehensive set of tasks demonstrates that Granite Code models consistently reaches state-of-the-art performance among available open-source code LLMs. The Granite Code model family was optimized for enterprise software development workflows and performs well across a range of coding tasks (e.g. code generation, fixing and explanation), making it a versatile all around code model. We release all our Granite Code models under an Apache 2.0 license for both research and commercial use.

Large language models (LLMs) have brought significant advancements to code generation and code repair, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, raises the risk of inadvertently propagating security vulnerabilities. Despite numerous studies investigating the safety of code LLMs, there remains a gap in comprehensively addressing their security features. In this work, we aim to present a comprehensive study aimed at precisely evaluating and enhancing the security aspects of code LLMs. To support our research, we introduce CodeSecEval, a meticulously curated dataset designed to address 44 critical vulnerability types with 180 distinct samples. CodeSecEval serves as the foundation for the automatic evaluation of code models in two crucial tasks: code generation and code repair, with a strong emphasis on security. Our experimental results reveal that current models frequently overlook security issues during both code generation and repair processes, resulting in the creation of vulnerable code. In response, we propose different strategies that leverage vulnerability-aware information and insecure code explanations to mitigate these security vulnerabilities. Furthermore, our findings highlight that certain vulnerability types particularly challenge model performance, influencing their effectiveness in real-world applications. Based on these findings, we believe our study will have a positive impact on the software engineering community, inspiring the development of improved methods for training and utilizing LLMs, thereby leading to safer and more trustworthy model deployment.

With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototyping and automated testing, but also augments developer efficiency through improved maintainability and reusability of code. In this paper, we introduce CodeIF, the first benchmark specifically designed to assess the abilities of LLMs to adhere to task-oriented instructions within diverse code generation scenarios. CodeIF encompasses a broad range of tasks, including function synthesis, error debugging, algorithmic refactoring, and code explanation, thereby providing a comprehensive suite to evaluate model performance across varying complexity levels and programming domains. We conduct extensive experiments with LLMs, analyzing their strengths and limitations in meeting the demands of these tasks. The experimental results offer valuable insights into how well current models align with human instructions, as well as the extent to which they can generate consistent, maintainable, and contextually relevant code. Our findings not only underscore the critical role that instruction-following LLMs can play in modern software development, but also illuminate pathways for future research aimed at enhancing their adaptability, reliability, and overall effectiveness in automated code generation.

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token "Sure"), potentially with multiple restarts. In this way, we achieve nearly 100\% attack success rate -- according to GPT-4 as a judge -- on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models -- that do not expose logprobs -- via either a transfer or prefilling attack with 100\% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models -- a task that shares many similarities with jailbreaking -- which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection). We provide the code, prompts, and logs of the attacks at https://github.com/tml-epfl/llm-adaptive-attacks.

Understanding and reasoning over diagrams is a fundamental aspect of human intelligence. While Large Multimodal Models (LMMs) have demonstrated impressive capabilities across various tasks, existing benchmarks lack comprehensive evaluation of their diagram interpretation and reasoning abilities, particularly in coding contexts. We present HumanEval-V, a rigorous benchmark of human-annotated coding tasks that spans six task types and evaluates diverse visual reasoning capabilities. Each task features carefully crafted diagrams paired with function signatures and test cases, employing novel code generation tasks to thoroughly assess models' diagram comprehension. Through extensive experiments with 22 LMMs, we find that even top-performing models achieve modest success rates, with Claude 3.5 Sonnet reaching only 36.8% pass@1, highlighting substantial room for improvement. Our analysis reveals that current LMMs struggle with spatial transformations, topological relationships, and dynamic patterns that humans find intuitive. These findings provide valuable insights for advancing LMMs' visual reasoning abilities. We have open-sourced our code and benchmark at https://github.com/HumanEval-V/HumanEval-V-Benchmark.

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities, requiring retraining whenever the catalog changes. We present HyDRA (Hybrid Dynamic Routing Architecture), a framework that predicts fine-grained, multi-dimensional capability requirements per query and matches them against configuration-defined model profiles via shortfall matching. A ModernBERT encoder with K=4 independent sigmoid heads scores each query along reasoning, code generation, debugging, and tool use; a shortfall-matching algorithm then selects the cheapest model whose capabilities meet the predicted requirements. The deployed predictor runs at 86 ms median CPU inference latency in production, and is fully decoupled from the model catalog -- adding or removing models requires only a configuration change, with zero retraining. On SWE-Bench Verified (5-model pool: GPT-5.4-mini, Claude Haiku 4.5, GPT-5.3 Codex, Claude Sonnet 4.6, GPT-5.4), HyDRA's tunable shortfall threshold spans three regimes: peak-quality exceeds the always-strong Claude Sonnet 4.6 baseline (75.4% vs. 74.2% resolution) at 12.9% cost savings; iso-quality matches Sonnet at 54.1% cost savings, a 6x improvement over our prior in-house binary router at 9.1%; aggressive pushes savings to 72.5% for a 3.2-point quality trade. Results generalize across LiveCodeBench, BigCodeBench, and tau-bench. HyDRA is deployed to all users in GitHub Copilot's VS Code Chat auto-mode and -- to our knowledge for the first time in the LLM routing literature -- demonstrates language-invariant routing across CJK, European, and other script families.

Refactoring is a common software engineering practice that improves code quality without altering program behavior. Although tools like ReExtractor+, RefactoringMiner, and RefDiff have been developed to detect refactorings automatically, they rely on complex rule definitions and static analysis, making them difficult to extend and generalize to other programming languages. In this paper, we investigate the viability of using foundation models for refactoring detection, implemented in a tool named RefModel. We evaluate Phi4-14B, and Claude 3.5 Sonnet on a dataset of 858 single-operation transformations applied to artificially generated Java programs, covering widely-used refactoring types. We also extend our evaluation by including Gemini 2.5 Pro and o4-mini-high, assessing their performance on 44 real-world refactorings extracted from four open-source projects. These models are compared against RefactoringMiner, RefDiff, and ReExtractor+. RefModel is competitive with, and in some cases outperform, traditional tools. In real-world settings, Claude 3.5 Sonnet and Gemini 2.5 Pro jointly identified 97% of all refactorings, surpassing the best-performing static-analysis-based tools. The models showed encouraging generalization to Python and Golang. They provide natural language explanations and require only a single sentence to define each refactoring type.

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis. To unlock this and demonstrate its effectiveness, we introduce LLM-as-a-Verifier, a general-purpose verification framework that provides fine-grained feedback for agentic tasks without requiring additional training. Unlike standard LM judges that prompt LLMs to produce discrete scores for candidate solutions, LLM-as-a-Verifier computes the expectation over the distribution of scoring token logits to generate continuous scores. This probabilistic formulation enables verification to scale along multiple dimensions: (1) score granularity, (2) repeated evaluation, and (3) criteria decomposition. In particular, we show that scaling the scoring granularity leads to better separation between positive and negative solutions, resulting in more calibrated comparisons. Moreover, scaling repeated evaluation and criteria decomposition consistently lead to additional gains in verification accuracy through variance and complexity reduction. We further introduce a cost-efficient ranking algorithm for selecting the best solution among candidates using the verifier's continuous scores. LLM-as-a-Verifier achieves state-of-the-art performance on Terminal-Bench V2 (86.5%), SWE-Bench Verified (78.2%), RoboRewardBench (87.4%), and MedAgentBench (73.3%). Beyond verification, the fine-grained signals from LLM-as-a-Verifier can also serve as a proxy for estimating task progress. We build an extension for Claude Code, enabling developers to monitor and improve their own agentic systems. Finally, we show that LLM-as-a-Verifier can provide dense feedback for RL, improving the sample efficiency of SAC and GRPO on robotics and mathematical reasoning benchmarks.

Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments of three public code language models when completing real-world code. We first developed an open-source IDE extension, Code4Me, for the online evaluation of the models. We collected real auto-completion usage data for over a year from more than 1200 users, resulting in over 600K valid completions. These models were then evaluated using six standard metrics across twelve programming languages. Next, we conducted a qualitative study of 1690 real-world completion requests to identify the reasons behind the poor model performance. A comparative analysis of the models' performance in online and offline settings was also performed, using benchmark synthetic datasets and two masking strategies. Our findings suggest that while developers utilize code completion across various languages, the best results are achieved for mainstream languages such as Python and Java. InCoder outperformed the other models across all programming languages, highlighting the significance of training data and objectives. Our study also revealed that offline evaluations do not accurately reflect real-world scenarios. Upon qualitative analysis of the model's predictions, we found that 66.3% of failures were due to the models' limitations, 24.4% occurred due to inappropriate model usage in a development context, and 9.3% were valid requests that developers overwrote. Given these findings, we propose several strategies to overcome the current limitations. These include refining training objectives, improving resilience to typographical errors, adopting hybrid approaches, and enhancing implementations and usability.

Agentic coding -- software development workflows in which autonomous coding agents plan, implement, and submit code changes with minimal human involvement -- is rapidly gaining traction. Prior work has shown that Pull Requests (PRs) produced using coding agents (Agentic-PRs) are accepted less often than PRs that are not labeled as agentic (Human-PRs). The rejection reasons for a single agent (Claude Code) have been explored, but a comparison of how rejection reasons differ between Agentic-PRs generated by different agents has not yet been performed. This comparison is important since different coding agents are often used for different purposes, which can lead to agent-specific failure patterns. In this paper, we inspect 654 rejected PRs from the AIDev dataset covering five coding agents, as well as a human baseline. Our results show that seven rejection modes occur only in Agentic-PRs, including distrust of AI-generated code. We also observe agent-specific patterns (e.g., automated withdrawal of inactive PRs by Devin), reflecting differences in how agents are configured and used in practice. Notably, a large proportion of rejected PRs (67.9%) lack explicit reviewer feedback, making their rejection reasons difficult to determine. To mitigate this issue, we propose a set of heuristics that reduce the proportion of such cases, offering a practical preprocessing step for future studies of PR rejection in agentic coding.

Large Language Models (LLMs) have shown significant advances in the past year. In addition to new versions of GPT and Llama, several other LLMs have been introduced recently. Some of these are open models available for download and modification. Although multilingual large language models have been available for some time, their performance on low-resourced languages such as Sinhala has been poor. We evaluated four recent LLMs on their performance directly in the Sinhala language, and by translation to and from English. We also evaluated their fine-tunability with a small amount of fine-tuning data. Claude and GPT 4o perform well out-of-the-box and do significantly better than previous versions. Llama and Mistral perform poorly but show some promise of improvement with fine tuning.

Computer-aided design (CAD) is the digital construction of 2D and 3D objects, and is central to a wide range of engineering and manufacturing applications like automobile and aviation. Despite its importance, CAD modeling remains largely a time-intensive, manual task. Recent works have attempted to automate this process with small transformer-based models and handcrafted CAD sequence representations. However, there has been little effort to leverage the potential of large language models (LLMs) for sequential CAD design. In this work, we introduce a new large-scale dataset of more than 170k CAD models annotated with high-quality, human-like descriptions generated with our pipeline based on GPT-4.1. Using this dataset, we fine-tune powerful code-LLMs to generate CAD sequences represented in a JSON-based format from natural language descriptions, demonstrating the viability and effectiveness of this approach for text-conditioned CAD generation. Because simple metrics often fail to reflect the quality of generated objects, we introduce geometric and topological metrics based on sphericity, mean curvature, and Euler characteristic to provide richer structural insights. Our experiments and ablation studies on both synthetic and human-annotated data demonstrate that CADmium is able to automate CAD design, drastically speeding up the design of new objects. The dataset, code, and fine-tuned models are available online.

A central aspect of machine learning research is experimentation, the process of designing and running experiments, analyzing the results, and iterating towards some positive outcome (e.g., improving accuracy). Could agents driven by powerful language models perform machine learning experimentation effectively? To answer this question, we introduce MLAgentBench, a suite of 13 tasks ranging from improving model performance on CIFAR-10 to recent research problems like BabyLM. For each task, an agent can perform actions like reading/writing files, executing code, and inspecting outputs. We then construct an agent that can perform ML experimentation based on ReAct framework. We benchmark agents based on Claude v1.0, Claude v2.1, Claude v3 Opus, GPT-4, GPT-4-turbo, Gemini-Pro, and Mixtral and find that a Claude v3 Opus agent is the best in terms of success rate. It can build compelling ML models over many tasks in MLAgentBench with 37.5% average success rate. Our agents also display highly interpretable plans and actions. However, the success rates vary considerably; they span from 100% on well-established older datasets to as low as 0% on recent Kaggle challenges created potentially after the underlying LM was trained. Finally, we identify several key challenges for LM-based agents such as long-term planning and reducing hallucination. Our code is released at https://github.com/snap-stanford/MLAgentBench.

Efficient creation of accurate and editable 3D CAD models is critical in engineering design, significantly impacting cost and time-to-market in product innovation. Current manual workflows remain highly time-consuming and demand extensive user expertise. While recent developments in AI-driven CAD generation show promise, existing models are limited by incomplete representations of CAD operations, inability to generalize to real-world images, and low output accuracy. This paper introduces CAD-Coder, an open-source Vision-Language Model (VLM) explicitly fine-tuned to generate editable CAD code (CadQuery Python) directly from visual input. Leveraging a novel dataset that we created--GenCAD-Code, consisting of over 163k CAD-model image and code pairs--CAD-Coder outperforms state-of-the-art VLM baselines such as GPT-4.5 and Qwen2.5-VL-72B, achieving a 100% valid syntax rate and the highest accuracy in 3D solid similarity. Notably, our VLM demonstrates some signs of generalizability, successfully generating CAD code from real-world images and executing CAD operations unseen during fine-tuning. The performance and adaptability of CAD-Coder highlights the potential of VLMs fine-tuned on code to streamline CAD workflows for engineers and designers. CAD-Coder is publicly available at: https://github.com/anniedoris/CAD-Coder.

As the use of large language models (LLMs) for code generation becomes more prevalent in software development, it is critical to enhance both the efficiency and correctness of the generated code. Existing methods and models primarily focus on the correctness of LLM-generated code, ignoring efficiency. In this work, we present Effi-Code, an approach to enhancing code generation in LLMs that can improve both efficiency and correctness. We introduce a Self-Optimization process based on Overhead Profiling that leverages open-source LLMs to generate a high-quality dataset of correct and efficient code samples. This dataset is then used to fine-tune various LLMs. Our method involves the iterative refinement of generated code, guided by runtime performance metrics and correctness checks. Extensive experiments demonstrate that models fine-tuned on the Effi-Code show significant improvements in both code correctness and efficiency across task types. For example, the pass@1 of DeepSeek-Coder-6.7B-Instruct generated code increases from 43.3\% to 76.8\%, and the average execution time for the same correct tasks decreases by 30.5\%. Effi-Code offers a scalable and generalizable approach to improving code generation in AI systems, with potential applications in software development, algorithm design, and computational problem-solving. The source code of Effi-Code was released in https://github.com/huangd1999/Effi-Code.

We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 1,000 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains(e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 191 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of 3 proprietary models and 11 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4V, Claude-3-opus only achieve an average score of 73.2 and 53.7, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence.

We propose Step-by-Step Coding (SBSC): a multi-turn math reasoning framework that enables Large Language Models (LLMs) to generate sequence of programs for solving Olympiad level math problems. At each step/turn, by leveraging the code execution outputs and programs of previous steps, the model generates the next sub-task and the corresponding program to solve it. This way, SBSC, sequentially navigates to reach the final answer. SBSC allows more granular, flexible and precise approach to problem-solving compared to existing methods. Extensive experiments highlight the effectiveness of SBSC in tackling competition and Olympiad-level math problems. For Claude-3.5-Sonnet, we observe SBSC (greedy decoding) surpasses existing state-of-the-art (SOTA) program generation based reasoning strategies by absolute 10.7% on AMC12, 8% on AIME and 12.6% on MathOdyssey. Given SBSC is multi-turn in nature, we also benchmark SBSC's greedy decoding against self-consistency decoding results of existing SOTA math reasoning strategies and observe performance gain by absolute 6.2% on AMC, 6.7% on AIME and 7.4% on MathOdyssey.

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from scientific Python repositories on GitHub, each paired with expert-authored patches and, on average, 264.6 community-maintained performance workloads per task, enabling the holistic ability of LLM agents to optimize codebases under realistic correctness and performance constraints. Our evaluations reveal that repository-scale, multi-objective optimization remains a major challenge for frontier LLM agents. Project website at: https://formula-code.github.io

The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code. This tech report describes the progress of the collaboration until December 2022, outlining the current state of the Personally Identifiable Information (PII) redaction pipeline, the experiments conducted to de-risk the model architecture, and the experiments investigating better preprocessing methods for the training data. We train 1.1B parameter models on the Java, JavaScript, and Python subsets of The Stack and evaluate them on the MultiPL-E text-to-code benchmark. We find that more aggressive filtering of near-duplicates can further boost performance and, surprisingly, that selecting files from repositories with 5+ GitHub stars deteriorates performance significantly. Our best model outperforms previous open-source multilingual code generation models (InCoder-6.7B and CodeGen-Multi-2.7B) in both left-to-right generation and infilling on the Java, JavaScript, and Python portions of MultiPL-E, despite being a substantially smaller model. All models are released under an OpenRAIL license at https://hf.co/bigcode.

As language models (LMs) advance, interest is growing in applying them to high-stakes societal decisions, such as determining financing or housing eligibility. However, their potential for discrimination in such contexts raises ethical concerns, motivating the need for better methods to evaluate these risks. We present a method for proactively evaluating the potential discriminatory impact of LMs in a wide range of use cases, including hypothetical use cases where they have not yet been deployed. Specifically, we use an LM to generate a wide array of potential prompts that decision-makers may input into an LM, spanning 70 diverse decision scenarios across society, and systematically vary the demographic information in each prompt. Applying this methodology reveals patterns of both positive and negative discrimination in the Claude 2.0 model in select settings when no interventions are applied. While we do not endorse or permit the use of language models to make automated decisions for the high-risk use cases we study, we demonstrate techniques to significantly decrease both positive and negative discrimination through careful prompt engineering, providing pathways toward safer deployment in use cases where they may be appropriate. Our work enables developers and policymakers to anticipate, measure, and address discrimination as language model capabilities and applications continue to expand. We release our dataset and prompts at https://huggingface.co/datasets/Anthropic/discrim-eval

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains requiring strict constraints. CodeGrad introduces a principled framework that integrates rigorous verification techniques directly into an iterative LLM-based generation loop. It uniquely treats code as a differentiable variable, converting structured feedback and mathematical constraints into a textual pseudo-gradient. This gradient guides the model to iteratively refine solutions, ensuring they are not only functional but also robust and mathematically justified. We evaluate CodeGrad on the HumanEval, HumanEval+, and LiveCodeBench benchmarks. Our implementation outperforms strong baselines, achieving an absolute improvement of up to 27% on HumanEval and a 41% relative improvement on the challenging LiveCodeBench V6. StructuredGrad generates mathematically justified code that is robust and efficient, paving the way for reliable AI-assisted software development in high-stakes applications.

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training.