ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Paper
•
2601.10156
•
Published
•
18
Yutao Mou
MurrayTom
AI & ML interests
AI Safety, Trustworthy Reasoning and Alignment of Large Language Models
Recent Activity
liked
a model
1 day ago
MurrayTom/TS-Guard
Organizations
None yet
authored
a
paper
1 day ago