lxp

lxpp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 1 day ago

lxpp/all_merged_instructions

Updated 1 day ago • 38

updated a dataset 3 days ago

lxpp/scicode-sft-data

Preview • Updated 3 days ago • 118

upvoted a paper 3 days ago

CoVEBench: Can Video Editing Models Handle Complex Instructions?

Paper • 2606.08415 • Published 5 days ago • 47

upvoted 3 papers 8 days ago

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Paper • 2606.02320 • Published 11 days ago • 14

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Paper • 2606.02060 • Published 11 days ago • 54

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Paper • 2606.01993 • Published 10 days ago • 14

upvoted 2 papers 24 days ago

OProver: A Unified Framework for Agentic Formal Theorem Proving

Paper • 2605.17283 • Published 26 days ago • 31

Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution

Paper • 2605.15301 • Published 29 days ago • 22

updated a dataset 24 days ago

NJU-LINK/WebCompass

Viewer • Updated 24 days ago • 933 • 10.7k • 6

published a dataset 29 days ago

lxpp/all_merged_instructions

Updated 1 day ago • 38

published a dataset about 1 month ago

lxpp/scicode-sft-data

Preview • Updated 3 days ago • 118

upvoted 2 papers about 1 month ago

SkillOS: Learning Skill Curation for Self-Evolving Agents

Paper • 2605.06614 • Published May 7 • 46

DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios

Paper • 2604.25914 • Published Apr 28 • 41

upvoted 3 papers about 2 months ago

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

Paper • 2604.18224 • Published Apr 20 • 22

DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation

Paper • 2604.14683 • Published Apr 16 • 36

CodeTracer: Towards Traceable Agent States

Paper • 2604.11641 • Published Apr 13 • 38

liked a dataset 2 months ago

NJU-LINK/WebCompass

Viewer • Updated 24 days ago • 933 • 10.7k • 6

published a dataset 2 months ago

NJU-LINK/WebCompass

Viewer • Updated 24 days ago • 933 • 10.7k • 6

upvoted a paper 3 months ago

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

Paper • 2603.00610 • Published Feb 28 • 35

upvoted a paper 4 months ago

AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations

Paper • 2602.03828 • Published Feb 3 • 20