Overseeing Agents Without Constant Oversight: Challenges and Opportunities
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914338593308672 |
|---|---|
| author | Grunde-McLaughlin, Madeleine Mozannar, Hussein Murad, Maya Chen, Jingya Amershi, Saleema Fourney, Adam |
| author_facet | Grunde-McLaughlin, Madeleine Mozannar, Hussein Murad, Maya Chen, Jingya Amershi, Saleema Fourney, Adam |
| contents | To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a Computer User Agent, we investigate the utility of basic action traces for verification, explore three alternatives via design probes, and test a novel interface's impact on error finding in question-answering tasks. As expected, we find that current practices are cumbersome, limiting their efficacy. Conversely, our proposed design reduced the time participants spent finding errors. However, although participants reported higher levels of confidence in their decisions, their final accuracy was not meaningfully improved. To this end, our study surfaces challenges for human verification of agentic systems, including managing built-in assumptions, users' subjective and changing correctness criteria, and the shortcomings, yet importance, of communicating the agent's process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16844 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Overseeing Agents Without Constant Oversight: Challenges and Opportunities Grunde-McLaughlin, Madeleine Mozannar, Hussein Murad, Maya Chen, Jingya Amershi, Saleema Fourney, Adam Human-Computer Interaction Artificial Intelligence To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a Computer User Agent, we investigate the utility of basic action traces for verification, explore three alternatives via design probes, and test a novel interface's impact on error finding in question-answering tasks. As expected, we find that current practices are cumbersome, limiting their efficacy. Conversely, our proposed design reduced the time participants spent finding errors. However, although participants reported higher levels of confidence in their decisions, their final accuracy was not meaningfully improved. To this end, our study surfaces challenges for human verification of agentic systems, including managing built-in assumptions, users' subjective and changing correctness criteria, and the shortcomings, yet importance, of communicating the agent's process. |
| title | Overseeing Agents Without Constant Oversight: Challenges and Opportunities |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2602.16844 |