用心理类型控制AI行为，让模型更懂人类思维模式。
Psychologically Enhanced AI Agents
- 通过提示词注入MBTI人格特质，引导AI在认知与情感上表现出不同倾向。
- 情感型AI在叙事任务中表现更佳，分析型AI在博弈场景中策略更稳定。
- 支持多智能体协作实验，自省可提升合作与推理质量，适合人机交互研究者。
我们提出MBTI-in-Thoughts框架，通过基于迈尔斯-布里格斯性格类型指标（MBTI）的心理学引导，增强大语言模型（LLM）代理的行为效果。该方法利用提示工程将不同人格原型注入代理，实现对人类心理中认知与情感两大核心维度的可控调节。实验证明，人格引导可使代理在多种任务中产生一致且可解释的行为偏差：情感型代理在叙事生成任务中表现更优，分析型代理在博弈论场景中采用更稳定的策略。该框架支持结构化多智能体通信协议的实验，并发现交互前自我反思能显著提升协作效率与推理质量。为确保人格特征的持续性，我们集成官方16Personalities测试进行自动验证。尽管聚焦于MBTI，我们的方法可无缝扩展至大五人格、HEXACO或九型人格等其他心理学体系。本研究在不进行微调的前提下，建立心理理论与大模型行为设计之间的桥梁，为心理增强型AI代理奠定基础。
原文摘要 · Abstract (English)
We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.
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。