MetaMind：基于元认知多智能体系统的人类社会思维建模
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
AI总结：
MetaMind是一个基于元认知的多智能体框架，通过三个协作阶段模拟人类社交推理，在真实社交场景和心智理论任务上分别提升35.7%和6.2%，首次使LLM达到人类水平。
摘要：
人类社交互动依赖于推断他人未言明的意图、情绪和信念的能力——这是一种基于心理学中“心智理论”（ToM）概念的认知技能。虽然大型语言模型（LLMs）在语义理解任务中表现出色，但它们在处理人类沟通中固有的模糊性和上下文细微差别时仍存在困难。为弥合这一差距，我们引入了MetaMind，一个受心理学元认知理论启发的多智能体框架，旨在模拟类似人类的社交推理。MetaMind将社交理解分解为三个协作阶段：（1）心智理论智能体生成关于用户心理状态（如意图、情绪）的假设，（2）道德智能体使用文化规范和伦理约束细化这些假设，（3）响应智能体生成上下文适当的响应，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上实现了最先进的性能，在真实世界社交场景中提升了35.7%，在ToM推理中提升了6.2%。值得注意的是，它首次使LLMs在关键ToM任务上达到人类水平的表现。消融研究证实了所有组件的必要性，展示了该框架在平衡上下文合理性、社交适当性和用户适应性方面的能力。这项工作推动AI系统向类人社交智能发展，在共情对话和文化敏感交互中具有应用前景。代码可在https://github.com/XMZhangAI/MetaMind获取。
英文摘要：
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 about user mental states (e.g., intent, emotion), (2) a Moral 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
