Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents
Tool-using language agents are vulnerable to indirect prompt injection, and a growing literature probes model internals to catch unsafe actions before they execute, with sharply conflicting results.
By Rishabh SinhaarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 30, 2026.
Comments
Sign in to join the discussion.