-
QUEST
🔎26Conduct thorough web‑based research and deliver detailed answers
-
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Paper • 2605.24218 • Published • 46 -
osunlp/QUEST-35B-RL
Text Generation • 35B • Updated • 979 • 24 -
osunlp/QUEST-RL-Data
Viewer • Updated • 1.13k • 4.97k • 2
AI & ML interests
Natural language processing, language models, language agents
Recent Activity
Papers
AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation
Beyond Clicking: A step towards generalist grounding via text dragging
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
SAEs for vision models like CLIP or DINOv2
Generative models to produce GCG-like adversarial suffixes
-
osunlp/AmpleGCG-llama2-sourced-llama2-7b-chat
Text Generation • 7B • Updated • 10 • 3 -
osunlp/AmpleGCG-llama2-sourced-vicuna-7b
Text Generation • 7B • Updated • 1 -
osunlp/AmpleGCG-llama2-sourced-vicuna-7b13b-guanaco-7b13b
Text Generation • 7B • Updated • 1 -
osunlp/AmpleGCG-plus-llama2-sourced-llama2-7b-chat
Text Generation • 7B • Updated • 3 • 2
Constructing Verifiable Environments for Data-Driven Discovery
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
-
osunlp/AutoElicit-Seed
Viewer • Updated • 361 • 30 • 1 -
osunlp/AutoElicit-Bench
Viewer • Updated • 117 • 68 • 1 -
osunlp/AutoElicit-Exec
Viewer • Updated • 132 • 5.54k • 1 -
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Paper • 2602.08235 • Published • 1
Evaluating Agentic Search with Agent-as-a-Judge
Towards Generalist Agents for the Web (NeurIPS'23 Spotlight)
Navigating GUIs as Humans Do: Universal Visual Grounding for GUI Agents (ICLR'25 Oral)
LLMs tuned on the SMolInstruct dataset for chemistry tasks.
-
QUEST
🔎26Conduct thorough web‑based research and deliver detailed answers
-
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Paper • 2605.24218 • Published • 46 -
osunlp/QUEST-35B-RL
Text Generation • 35B • Updated • 979 • 24 -
osunlp/QUEST-RL-Data
Viewer • Updated • 1.13k • 4.97k • 2
Constructing Verifiable Environments for Data-Driven Discovery
Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
-
osunlp/AutoElicit-Seed
Viewer • Updated • 361 • 30 • 1 -
osunlp/AutoElicit-Bench
Viewer • Updated • 117 • 68 • 1 -
osunlp/AutoElicit-Exec
Viewer • Updated • 132 • 5.54k • 1 -
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Paper • 2602.08235 • Published • 1
Beyond Clicking: A step towards generalist grounding via text dragging
Evaluating Agentic Search with Agent-as-a-Judge
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
Towards Generalist Agents for the Web (NeurIPS'23 Spotlight)
SAEs for vision models like CLIP or DINOv2
Navigating GUIs as Humans Do: Universal Visual Grounding for GUI Agents (ICLR'25 Oral)
Generative models to produce GCG-like adversarial suffixes
-
osunlp/AmpleGCG-llama2-sourced-llama2-7b-chat
Text Generation • 7B • Updated • 10 • 3 -
osunlp/AmpleGCG-llama2-sourced-vicuna-7b
Text Generation • 7B • Updated • 1 -
osunlp/AmpleGCG-llama2-sourced-vicuna-7b13b-guanaco-7b13b
Text Generation • 7B • Updated • 1 -
osunlp/AmpleGCG-plus-llama2-sourced-llama2-7b-chat
Text Generation • 7B • Updated • 3 • 2
LLMs tuned on the SMolInstruct dataset for chemistry tasks.