MetaMind：運用元認知多智能體系統模擬人類社會思維

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

人類的社會互動依賴於推斷他人未言明的意圖、情感和信念的能力——這一認知技能植根於心理學中的「心智理論」（Theory of Mind, ToM）概念。儘管大型語言模型（LLMs）在語義理解任務中表現出色，但它們在處理人類交流中固有的模糊性和語境細微差別時仍面臨挑戰。為彌合這一差距，我們提出了MetaMind，這是一個受元認知心理學理論啟發的多智能體框架，旨在模擬人類的社會推理能力。MetaMind將社會理解分解為三個協作階段：(1) 心智理論智能體生成用戶心理狀態（如意圖、情感）的假設，(2) 領域智能體利用文化規範和倫理約束對這些假設進行精煉，(3) 回應智能體生成語境適宜的回應，同時驗證其與推斷意圖的一致性。我們的框架在三個具有挑戰性的基準測試中達到了最先進的性能，在現實世界社交場景中提升了35.7%，在心智理論推理中提升了6.2%。值得注意的是，它首次使LLMs在關鍵心智理論任務上達到了人類水平。消融研究證明了所有組件的必要性，展示了框架在平衡語境合理性、社會適宜性和用戶適應性方面的能力。這項工作推動了AI系統向類人社會智能邁進，並在同理心對話和文化敏感互動中具有應用潛力。代碼可在https://github.com/XMZhangAI/MetaMind 獲取。

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.