@inproceedings{adavi2026agentpushback,
author = {Adavi, Krishna Akhil Kumar and Ghosh, Pratik and Banks, Richard and Sarkar, Advait and Lindley, Si\^{a}n E.},
title = {"Will This Tool Ever Push Back or Challenge Me?": Reflections on a Multi-agent LLM Tool for Perspective Seeking},
year = {2026},
isbn = {9798400724299},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3808045.3808058},
doi = {10.1145/3808045.3808058},
abstract = {The ability of LLM-based agents to role-play may be especially helpful for gathering multiple perspectives in problem-solving situations. To understand how workers would respond to getting perspectives from agents, we conducted an interview study with 18 knowledge workers using a generative AI-powered multi-agent design probe. Participants described their current practices of perspective seeking from people, and outlined challenges with this practice including not knowing the right person to speak to and anxiety around reaching out. Participants reported finding value in the probe when it produced responses that aligned with their current solutions, and wanted sources or explanations for solutions they were unfamiliar with. They especially highlighted the need to be challenged by the probe, and were worried that the availability of such tools would reduce their interactions with colleagues. We discuss implications for designing for challenge, and locate agents as preparation tools for interacting with colleagues.},
booktitle = {Proceedings of the 5th Annual Symposium on Human-Computer Interaction for Work},
articleno = {15},
numpages = {16},
keywords = {Knowledge Sharing, Help Seeking, Perspective Seeking, Advice Seeking, Information Seeking, Multi-agent LLMs},
location = {
},
series = {CHIWORK '26}
}