OpenSafetyLab

AI & ML interests

None defined yet.

Recent Activity

adwardlee  authored a paper 2 days ago

Toward Efficient Agents: Memory, Tool learning, and Planning

adwardlee  authored a paper 4 days ago

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

adwardlee  submitted a paper 5 days ago

Toward Efficient Agents: Memory, Tool learning, and Planning

View all activity

Team members 4