# Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach

arXiv: https://arxiv.org/abs/2208.11660 · HTML: https://mlsanity.com/paper/2208.11660/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2022.

## Built on by (most cited first, 16 of 16)

- [Emergent Coordination in Multi-Agent Language Models](https://mlsanity.com/paper/2510.05174/) (2025)
- [Capturing Humans' Mental Models of AI: An Item Response Theory Approach](https://mlsanity.com/paper/2305.09064/) (2023)
- [Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2410.17373/) (2024)
- [Optimizing Delegation in Collaborative Human-AI Hybrid Teams](https://mlsanity.com/paper/2402.05605/) (2024)
- [Boosting Team Modeling through Tempo-Relational Representation Learning](https://mlsanity.com/paper/2507.13305/) (2025)
- [MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind](https://mlsanity.com/paper/2603.00808/) (2026)
- [Optimizing Risk-averse Human-AI Hybrid Teams](https://mlsanity.com/paper/2403.08386/) (2024)
- [An AI Theory of Mind Will Enhance Our Collective Intelligence](https://mlsanity.com/paper/2411.09168/) (2024)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration](https://mlsanity.com/paper/2406.06051/) (2024)
- [Large Language Models for Automatic Milestone Detection in Group Discussions](https://mlsanity.com/paper/2406.10842/) (2024)
- [Enhancing Collective Intelligence in Large Language Models Through Emotional Integration](https://mlsanity.com/paper/2503.04849/) (2025)
- [Controllable Complementarity: Subjective Preferences in Human-AI Collaboration](https://mlsanity.com/paper/2503.05455/) (2025)
- [Bounded Normative Equivalence in Human-AI Cooperation: Group Behaviour, Not Partner Labels, Predicts Cooperation under Anonymous Aggregate Feedback](https://mlsanity.com/paper/2601.20487/) (2026)
- [From Overload to Convergence: Supporting Multi-Issue Human-AI Negotiation with Bayesian Visualization](https://mlsanity.com/paper/2603.22766/) (2026)
- [Artificial collectives of specialists and generalists excel at different tasks](https://mlsanity.com/paper/2606.20877/) (2026)

## Abstract (arXiv)

We develop a network of Bayesian agents that collectively model the mental states of teammates from the observed communication. Using a generative computational approach to cognition, we make two contributions. First, we show that our agent could generate interventions that improve the collective intelligence of a human-AI team beyond what humans alone would achieve. Second, we develop a real-time measure of human's theory of mind ability and test theories about human cognition. We use data collected from an online experiment in which 145 individuals in 29 human-only teams of five communicate through a chat-based system to solve a cognitive task. We find that humans (a) struggle to fully integrate information from teammates into their decisions, especially when communication load is high, and (b) have cognitive biases which lead them to underweight certain useful, but ambiguous, information. Our theory of mind ability measure predicts both individual- and team-level performance. Observing teams' first 25% of messages explains about 8% of the variation in final team performance, a 170% improvement compared to the current state of the art.