Metamind: General And Cognitive World Models In Multi-agent Systems By Meta-theory Of Mind

Abstract

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 b

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2026metamind

Related papers

• Theory Of Mind As Intrinsic Motivation For Multi-agent Reinforcement Learning (2023)0.00
• Learning In Cooperative Multiagent Systems Using Cognitive And Machine Models (2023)7.81
• Theory Of Minds: Understanding Behavior In Groups Through Inverse Planning (2019)0.00
• A Theory Of Mind Approach As Test-time Mitigation Against Emergent Adversarial Communication (2023)0.00
• Innate-values-driven Reinforcement Learning Based Cooperative Multi-agent Cognitive Modeling (2024)0.00
• Understanding The World To Solve Social Dilemmas Using Multi-agent Reinforcement Learning (2023)0.00
• General Agents Contain World Models (2025)0.00
• Foundation World Models For Agents That Learn, Verify, And Adapt Reliably Beyond Static Environments (2026)0.00