OpenSafetyLab

non-profit

https://open-trust-lab.vercel.app

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

adwardlee authored a paper about 20 hours ago

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

adwardlee submitted a paper 1 day ago

Toward Efficient Agents: Memory, Tool learning, and Planning

adwardlee submitted a paper 6 days ago

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

View all activity

OpenSafetyLab 's Spaces 2

Salad Bench Leaderboard

Display benchmark results for models across different taxonomies

README