MetaMind：运用元认知多智能体系统模拟人类社交思维

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

May 25, 2025

作者: Xuanming Zhang, Yuxuan Chen, Min-Hsuan Yeh, Yixuan Li

cs.AI

摘要

人类社交互动依赖于推断他人未言明的意图、情感和信念的能力——这一认知技能植根于心理学的“心智理论”（Theory of Mind, ToM）概念。尽管大型语言模型（LLMs）在语义理解任务上表现出色，但它们难以应对人类交流中固有的模糊性和上下文细微差别。为弥合这一差距，我们引入了MetaMind，一个受元认知心理学理论启发的多智能体框架，旨在模拟类人的社会推理能力。MetaMind将社会理解分解为三个协作阶段：(1) 心智理论智能体生成用户心理状态（如意图、情绪）的假设，(2) 领域智能体利用文化规范和伦理约束精炼这些假设，(3) 响应智能体生成上下文适宜的回应，同时验证与推断意图的一致性。我们的框架在三个具有挑战性的基准测试中实现了最先进的性能，在现实世界社交场景中提升了35.7%，在心智理论推理上提升了6.2%。尤为重要的是，它首次使LLMs在关键心智理论任务上达到了人类水平的表现。消融研究证实了所有组件的必要性，展示了框架在平衡上下文合理性、社交适宜性和用户适应性方面的能力。这项工作推动了AI系统向类人社交智能迈进，在共情对话和文化敏感互动中具有广泛应用。代码可在https://github.com/XMZhangAI/MetaMind获取。

English

Human social interactions depend on the ability to infer others' unspoken intentions, emotions, and beliefs-a cognitive skill grounded in the psychological concept of Theory of Mind (ToM). While large language models (LLMs) excel in semantic understanding tasks, they struggle with the ambiguity and contextual nuance inherent in human communication. To bridge this gap, we introduce MetaMind, a multi-agent framework inspired by psychological theories of metacognition, designed to emulate human-like social reasoning. MetaMind decomposes social understanding into three collaborative stages: (1) a Theory-of-Mind Agent generates hypotheses user mental states (e.g., intent, emotion), (2) a Domain Agent refines these hypotheses using cultural norms and ethical constraints, and (3) a Response Agent generates contextually appropriate responses while validating alignment with inferred intent. Our framework achieves state-of-the-art performance across three challenging benchmarks, with 35.7% improvement in real-world social scenarios and 6.2% gain in ToM reasoning. Notably, it enables LLMs to match human-level performance on key ToM tasks for the first time. Ablation studies confirm the necessity of all components, which showcase the framework's ability to balance contextual plausibility, social appropriateness, and user adaptation. This work advances AI systems toward human-like social intelligence, with applications in empathetic dialogue and culturally sensitive interactions. Code is available at https://github.com/XMZhangAI/MetaMind.