works on
co-evolution training 1computer-use agents 1reinforcement learning 1stateful applications 1synthetic environments 1

From the 1 of 8 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

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

Aradhye Agarwal, Gurdit Siyan, Yash Pandya +3

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, su…