AI RESEARCH
UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind
arXiv CS.AI
•
ArXi:2605.27721v1 Announce Type: cross Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mind (ToM) tasks, where success requires reasoning from the user's perspective. However, many existing approaches address ToM with complex pipelines that model behavior indirectly, without explicitly reconstructing the user's mental state.