# MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind arXiv: https://arxiv.org/abs/2603.00808 ยท HTML: https://mlsanity.com/paper/2603.00808/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in World models for language agents, one of 11 directions in World models. - Builds on 43 of its 57 references that are in the map. - First posted on arXiv 28 Feb 2026. ## Placed in - World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/) ## Builds on (most cited first, 30 of 43) - [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021) - [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025) - [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023) - [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024) - [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018) - [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024) - [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023) - [Evaluating the World Model Implicit in a Generative Model](https://mlsanity.com/paper/2406.03689/) (2024) - [Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving](https://mlsanity.com/paper/2408.14197/) (2024) - [ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind](https://mlsanity.com/paper/2111.09189/) (2021) - [MuMA-ToM: Multi-modal Multi-Agent Theory of Mind](https://mlsanity.com/paper/2408.12574/) (2024) - [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024) - [Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models](https://mlsanity.com/paper/2407.07086/) (2024) - [Mastering Memory Tasks with World Models](https://mlsanity.com/paper/2403.04253/) (2024) - [Theory of Minds: Understanding Behavior in Groups Through Inverse Planning](https://mlsanity.com/paper/1901.06085/) (2019) - [Too many cooks: Bayesian inference for coordinating multi-agent collaboration](https://mlsanity.com/paper/2003.11778/) (2020) - [Learning Latent Dynamic Robust Representations for World Models](https://mlsanity.com/paper/2405.06263/) (2024) - [Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2307.01158/) (2023) - [Neural Recursive Belief States in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.02274/) (2021) - [Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach](https://mlsanity.com/paper/2208.11660/) (2022) - [Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization](https://mlsanity.com/paper/2403.10967/) (2024) - [Intent-aware Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1803.02018/) (2018) - [Multiagent Inverse Reinforcement Learning via Theory of Mind Reasoning](https://mlsanity.com/paper/2302.10238/) (2023) - [Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models](https://mlsanity.com/paper/2406.15836/) (2024) - [A Review on Machine Theory of Mind](https://mlsanity.com/paper/2303.11594/) (2023) - [Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective](https://mlsanity.com/paper/2505.20922/) (2025) - [Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback](https://mlsanity.com/paper/2512.22336/) (2025) - [Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning](https://mlsanity.com/paper/2305.15260/) (2023) - [PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2508.02159/) (2025) - [Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data](https://mlsanity.com/paper/2103.04289/) (2021) ## Built on by (most cited first, 3 of 3) - [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026) - [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026) - [From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks](https://mlsanity.com/paper/2608.06227/) (2026) ## Abstract (arXiv) A major challenge for world models in multi-agent systems is to understand interdependent agent dynamics, predict interactive multi-agent trajectories, and plan over long horizons with collective awareness, without centralized supervision or explicit communication. In this paper, MetaMind, a general and cognitive world model for multi-agent systems that leverages a novel meta-theory of mind (Meta-ToM) framework, is proposed. Through MetaMind, each agent learns not only to predict and plan over its own beliefs, but also to inversely reason goals and beliefs from its own behavior trajectories. This self-reflective, bidirectional inference loop enables each agent to learn a metacognitive ability in a self-supervised manner. Then, MetaMind is shown to generalize the metacognitive ability from first-person to third-person through analogical reasoning. Thus, in multi-agent systems, each agent with MetaMind can actively reason about goals and beliefs of other agents from limited, observable behavior trajectories in a zero-shot manner, and then adapt to emergent collective intention without an explicit communication mechanism. Extended simulation results on diverse multi-agent tasks demonstrate that MetaMind can achieve superior task performance and outperform baselines in few-shot multi-agent generalization.