让大模型具备理解他人心理的能力，对话更聪明、关系更融洽。
Infusing Theory of Mind into Socially Intelligent LLM Agents
- 用心理理论显式建模对话中对方的意图与状态
- 在Sotopia基准上对话目标达成率显著优于基线
- 适合构建有长期策略和情感智慧的智能对话系统
心智理论（ToM）——理解他人心理状态的能力——是人类社交智能的核心，但现有聊天机器人和基于大模型的社会代理通常缺乏这一能力。本文表明，显式引入ToM的大模型在对话中表现更优，能更有效地达成目标。我们发现，仅通过提示模型在对话回合间生成心理状态，就已带来显著提升；在此基础上，提出面向心智理论的对话代理ToMAgent（ToMA），通过将心理状态与对话前瞻结合进行训练，使生成的心理状态对实现对话目标最具价值。在Sotopia交互式社会评估基准上的实验表明，该方法优于多种基线。综合分析显示，ToMA展现出更具策略性、目标导向的推理行为，支持长周期适应，同时维持更良好的合作关系。结果表明，该研究推动了心智理论在构建社会智能大模型代理中的应用。
原文摘要 · Abstract (English)
Theory of Mind (ToM)-an understanding of the mental states of others-is a key aspect of human social intelligence, yet, chatbots and LLM-based social agents do not typically integrate it. In this work, we demonstrate that LLMs that explicitly use ToM get better at dialogue, achieving goals more effectively. After showing that simply prompting models to generate mental states between dialogue turns already provides significant benefit, we further introduce ToMAgent (ToMA), a ToM-focused dialogue agent. ToMA is trained by pairing ToM with dialogue lookahead to produce mental states that are maximally useful for achieving dialogue goals. Experiments on the Sotopia interactive social evaluation benchmark demonstrate the effectiveness of our method over a range of baselines. Comprehensive analysis shows that ToMA exhibits more strategic, goal-oriented reasoning behaviors, which enable long-horizon adaptation, while maintaining better relationships with their partners. Our results suggest a step forward in integrating ToM for building socially intelligent LLM agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。