Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Agarwal, Aradhye, Siyan, Gurdit, Pandya, Yash, Singh, Joykirat, Nambi, Akshay, Awadallah, Ahmed
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.03205