# Theory of Minds: Understanding Behavior in Groups Through Inverse Planning

arXiv: https://arxiv.org/abs/1901.06085 · HTML: https://mlsanity.com/paper/1901.06085/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2019.

## Built on by (most cited first, 30 of 30)

- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [EgoTaskQA: Understanding Human Tasks in Egocentric Videos](https://mlsanity.com/paper/2210.03929/) (2022)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind](https://mlsanity.com/paper/2111.09189/) (2021)
- [Visual cognition in multimodal large language models](https://mlsanity.com/paper/2311.16093/) (2023)
- [Language Models Represent Beliefs of Self and Others](https://mlsanity.com/paper/2402.18496/) (2024)
- [Learning to Cooperate with Humans using Generative Agents](https://mlsanity.com/paper/2411.13934/) (2024)
- [Cognitive science as a source of forward and inverse models of human decisions for robotics and control](https://mlsanity.com/paper/2109.00127/) (2021)
- [Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions](https://mlsanity.com/paper/2404.11023/) (2024)
- [Inferring the Goals of Communicating Agents from Actions and Instructions](https://mlsanity.com/paper/2306.16207/) (2023)
- [Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination](https://mlsanity.com/paper/2504.12714/) (2025)
- [Emergent Prosociality in Multi-Agent Games Through Gifting](https://mlsanity.com/paper/2105.06593/) (2021)
- [Social Contract AI: Aligning AI Assistants with Implicit Group Norms](https://mlsanity.com/paper/2310.17769/) (2023)
- [MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models](https://mlsanity.com/paper/2502.16671/) (2025)
- [Neural Amortized Inference for Nested Multi-agent Reasoning](https://mlsanity.com/paper/2308.11071/) (2023)
- [Inverse Reinforcement Learning from a Gradient-based Learner](https://mlsanity.com/paper/2007.07812/) (2020)
- [Modeling Others' Minds as Code](https://mlsanity.com/paper/2510.01272/) (2025)
- [Modeling Communication to Coordinate Perspectives in Cooperation](https://mlsanity.com/paper/2106.02164/) (2021)
- [A Cognitive Framework for Delegation Between Error-Prone AI and Human Agents](https://mlsanity.com/paper/2204.02889/) (2022)
- [Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner](https://mlsanity.com/paper/2506.01301/) (2025)
- [Evaluating LLMs in Open-Source Games](https://mlsanity.com/paper/2512.00371/) (2025)
- [Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective](https://mlsanity.com/paper/2106.05402/) (2021)
- [Learning Intuitive Policies Using Action Features](https://mlsanity.com/paper/2201.12658/) (2022)
- [Inverse Attention Agents for Multi-Agent Systems](https://mlsanity.com/paper/2410.21794/) (2024)
- [MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind](https://mlsanity.com/paper/2603.00808/) (2026)
- [DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories](https://mlsanity.com/paper/2604.20443/) (2026)
- [Modeling Human Behavior Part I -- Learning and Belief Approaches](https://mlsanity.com/paper/2205.06485/) (2022)
- [An AI Theory of Mind Will Enhance Our Collective Intelligence](https://mlsanity.com/paper/2411.09168/) (2024)
- [Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows](https://mlsanity.com/paper/2604.20658/) (2026)
- [Improving Human-Robot Collaboration via Computational Design](https://mlsanity.com/paper/2303.11425/) (2023)

## Abstract (arXiv)

Human social behavior is structured by relationships. We form teams, groups, tribes, and alliances at all scales of human life. These structures guide multi-agent cooperation and competition, but when we observe others these underlying relationships are typically unobservable and hence must be inferred. Humans make these inferences intuitively and flexibly, often making rapid generalizations about the latent relationships that underlie behavior from just sparse and noisy observations. Rapid and accurate inferences are important for determining who to cooperate with, who to compete with, and how to cooperate in order to compete. Towards the goal of building machine-learning algorithms with human-like social intelligence, we develop a generative model of multi-agent action understanding based on a novel representation for these latent relationships called Composable Team Hierarchies (CTH). This representation is grounded in the formalism of stochastic games and multi-agent reinforcement learning. We use CTH as a target for Bayesian inference yielding a new algorithm for understanding behavior in groups that can both infer hidden relationships as well as predict future actions for multiple agents interacting together. Our algorithm rapidly recovers an underlying causal model of how agents relate in spatial stochastic games from just a few observations. The patterns of inference made by this algorithm closely correspond with human judgments and the algorithm makes the same rapid generalizations that people do.