Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Paper
• 2603.03205 • Published
• 8
Akshay Nambi
akshaynambi
AI & ML interests
None yet
Recent Activity
submitted
a paper
1 day ago
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use authored
a paper
3 months ago
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive,
Attentive Compression Organizations
None yet