Abstract:Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 36.8% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.
| Comments: | Preprint |
| Subjects: | Computation and Language (cs.CL); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2602.17588 [cs.CL] |
| (or arXiv:2602.17588v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2602.17588 arXiv-issued DOI via DataCite |
Submission history
From: Faria Huq [view email]
[v1]
Thu, 19 Feb 2026 18:11:28 UTC (14,011 KB)
[v2]
Fri, 27 Feb 2026 05:29:41 UTC (14,011 KB)
[v3]
Sun, 31 May 2026 08:32:10 UTC (13,752 KB)