# Improving Multi-Agent Cooperation using Theory of Mind

arXiv: https://arxiv.org/abs/2007.15703 · HTML: https://mlsanity.com/paper/2007.15703/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 7 of 7)

- [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023)
- [ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind](https://mlsanity.com/paper/2111.09189/) (2021)
- [Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information](https://mlsanity.com/paper/2408.02559/) (2024)
- [Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning](https://mlsanity.com/paper/2507.03682/) (2025)
- [Preventing Rogue Agents Improves Multi-Agent Collaboration](https://mlsanity.com/paper/2502.05986/) (2025)
- [Using High-Level Patterns to Estimate How Humans Predict a Robot will Behave](https://mlsanity.com/paper/2409.13533/) (2024)
- [S3IT: A Benchmark for Spatially Situated Social Intelligence Test](https://mlsanity.com/paper/2512.19992/) (2025)

## Abstract (arXiv)

Recent advances in Artificial Intelligence have produced agents that can beat human world champions at games like Go, Starcraft, and Dota2. However, most of these models do not seem to play in a human-like manner: People infer others' intentions from their behaviour, and use these inferences in scheming and strategizing. Here, using a Bayesian Theory of Mind (ToM) approach, we investigated how much an explicit representation of others' intentions improves performance in a cooperative game. We compared the performance of humans playing with optimal-planning agents with and without ToM, in a cooperative game where players have to flexibly cooperate to achieve joint goals. We find that teams with ToM agents significantly outperform non-ToM agents when collaborating with all types of partners: non-ToM, ToM, as well as human players, and that the benefit of ToM increases the more ToM agents there are. These findings have implications for designing better cooperative agents.