# A Review on Machine Theory of Mind

arXiv: https://arxiv.org/abs/2303.11594 · HTML: https://mlsanity.com/paper/2303.11594/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 80 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 17 of 17)

- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration](https://mlsanity.com/paper/2010.09890/) (2020)
- [Online Bayesian Goal Inference for Boundedly-Rational Planning Agents](https://mlsanity.com/paper/2006.07532/) (2020)
- [Evaluating Theory of Mind in Question Answering](https://mlsanity.com/paper/1808.09352/) (2018)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others](https://mlsanity.com/paper/2102.11938/) (2021)
- [Too many cooks: Bayesian inference for coordinating multi-agent collaboration](https://mlsanity.com/paper/2003.11778/) (2020)
- [An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1806.03820/) (2018)
- [Who is Mistaken?](https://mlsanity.com/paper/1612.01175/) (2016)
- [BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios](https://mlsanity.com/paper/2206.10665/) (2022)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Learning Theory of Mind via Dynamic Traits Attribution](https://mlsanity.com/paper/2204.09047/) (2022)
- [The Complexity of Limited Belief Reasoning -- The Quantifier-Free Case](https://mlsanity.com/paper/1805.02912/) (2018)

## Built on by (most cited first, 9 of 9)

- [SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals](https://mlsanity.com/paper/2406.04784/) (2024)
- [BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind](https://mlsanity.com/paper/2402.07402/) (2024)
- [Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models](https://mlsanity.com/paper/2411.15999/) (2024)
- [MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind](https://mlsanity.com/paper/2603.00808/) (2026)
- [An AI Theory of Mind Will Enhance Our Collective Intelligence](https://mlsanity.com/paper/2411.09168/) (2024)
- [Situated, Dynamic, and Subjective: Envisioning the Design of Theory-of-Mind-Enabled Everyday AI with Industry Practitioners](https://mlsanity.com/paper/2602.11342/) (2026)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [Machine Theory of Mind and the Structure of Human Values](https://mlsanity.com/paper/2505.20342/) (2025)
- [Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks](https://mlsanity.com/paper/2605.18194/) (2026)

## Abstract (arXiv)

Theory of Mind (ToM) is the ability to attribute mental states to others, the basis of human cognition. At present, there has been growing interest in the AI with cognitive abilities, for example in healthcare and the motoring industry. Beliefs, desires, and intentions are the early abilities of infants and the foundation of human cognitive ability, as well as for machine with ToM. In this paper, we review recent progress in machine ToM on beliefs, desires, and intentions. And we shall introduce the experiments, datasets and methods of machine ToM on these three aspects, summarize the development of different tasks and datasets in recent years, and compare well-behaved models in aspects of advantages, limitations and applicable conditions, hoping that this study can guide researchers to quickly keep up with latest trend in this field. Unlike other domains with a specific task and resolution framework, machine ToM lacks a unified instruction and a series of standard evaluation tasks, which make it difficult to formally compare the proposed models. We argue that, one method to address this difficulty is now to present a standard assessment criteria and dataset, better a large-scale dataset covered multiple aspects of ToM.