arXiv (All)
open access
Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision
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
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Discriminative World Models for Web Agents#632822
- MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models#1144074
- Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection#1063071
- ALDER: Discovering the Laws of a World by Acting in It#1118801
- Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents#1063564
Record · ID 822464
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive