不同性格组合影响大模型团队表现，任务结构决定性格是否关键。
When Does Personality Composition Matter for Multi-Agent LLM Teams?
- 通过操控大模型性格特质，研究多智能体协作中的沟通风格变化。
- 编码任务中低亲和性仅改变沟通方式，不影响里程碑完成；开放协作与谈判中则严重拖累表现。
- 揭示性格设计对系统性能的边界条件，指导智能体系统架构优化。
性格提示能改变大语言模型的沟通方式，但这种行为变化是否影响客观任务结果仍缺乏系统研究。已有工作表明，低亲和性提示导致对抗性语言，高亲和性提示则促进合作，但沟通风格与任务绩效之间的关系尚未在多个领域被系统检验。本文在三个任务领域——结构化编码、开放式研究协作和竞争性谈判——中，操纵前沿大模型的性格特质，探究性格组合对多智能体团队表现的影响。结果发现，性格效应高度依赖任务结构：在编码任务中，低亲和性引发显著沟通变化，但几乎不影响里程碑完成率；而在开放协作与谈判任务中，相同干预导致性能大幅下降。研究为多智能体系统设计提供启示，并指出性格操控的局限性。
原文摘要 · Abstract (English)
Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-explored. Prior work shows that agents prompted with low agreeableness produce adversarial language, while those prompted with high agreeableness become cooperative, but the relationship between communication style and task performance has not been systematically examined across multiple domains. In this work, we investigate whether personality composition matters for multi-agent team performance by manipulating personality traits across frontier LLMs on three task domains: structured coding, open-ended research collaboration, and competitive bargaining. We find that personality effects depend critically on task structure. In coding tasks, low agreeableness leads to large communication shifts that have little effect on milestone completion. In open-ended collaboration and bargaining, the same manipulation substantially degrades performance. We discuss implications for multi-agent system design and the limits of personality manipulation.
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。