cs.AI · 2603.18786 Copy arXiv ID · Mar 19, 2026 Save Proceedings of the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind Authors: Nitay Alon , Joseph M. Barnby , Reuth Mirsky , Stefan Sarkadi
In Abstract This volume includes a selection of papers presented at the 2nd Workshop on Advancing Artificial Intelligence through Theory of Mind held at AAAI 2026 in Singapore on 26th January 2026. The purpose of this volume is to provide an open access and curated anthology for the ToM and AI research community.
More in this topic Theory of Mind studies how people and AI infer others’ beliefs, goals, and knowledge to predict behavior and coordinate interaction.
See all 92 papers → May 12, 2026 · Patrick Callaghan, Reid Simmons, Henny Admoni Theory of Mind
Robotics Institute, Carnegie Mellon University
May 11, 2026 · Gurusha Juneja, Dylan Lu, Saaket Agashe +7 Multi-Agent Coordination Theory of Mind
University of California, Santa Barbara · 2King’s College London · 3Cisco Research
Apr 28, 2026 · Nanxu Gong, Zixin Chen, Haotian Li +5 LLM Evaluation Theory of Mind
Arizona State University · Hong Kong University of Science and Technology · Microsoft Research Asia +1
May 12, 2026 J/K move · Enter open · S save
Patrick Callaghan, Reid Simmons, Henny Admoni
Robotics Institute, Carnegie Mellon University
Discrepancies between an agent's actual knowledge and what a person thinks the agent knows can hinder interactions. If an agent could detect such discrepancies, it could provide feedback to account for them and improve current and future interactions. Using the I-POMDP as a framework for a second-order Theory of Mind (ToM-2), this work endows an agent with the ability to model the evolution of a person's erroneous beliefs about an agent and the cognitive biases and heuristics (CBH) from which they arise. In doing so, the agent can detect when CBH might be at play during an interaction and adaptively generate feedback that accounts for them. An in-person user study shows how a ToM-2 learner can account for the effects of a teacher's CBH to significantly improve the informativeness of teacher actions, and subjective results suggest people find the ToM-2 learner's feedback more useful.