Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision

arXiv cs.AISeptember 3, 2026en

arXiv:2609.02057v1 Announce Type: new Abstract: Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token logits are unavailable. In this work, we study prefix-level risk prediction for web agents using observable trajectory signals: given an evolving prefix, estimate whether the current execution remains on track or is tending toward failure. We derive two observable trajectory representations: Macro features summarize cross-step agent--environment behavior and feedback, while Micro features measure the consistency of intention, action, and anticipated state change through repeated black-box queries. Instead of inheriting the final result label, we lab

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning
• Agenter