SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType

paper

region

Global