Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Paper
• 2603.03205 • Published
• 5
Yash Pandya
yashp96
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use liked
a model 2 months ago
microsoft/Fara-7B upvoted a paper 10 months ago
Agentic Reasoning and Tool Integration for LLMs via Reinforcement
Learning Organizations
None yet
