人格构成何时对多智能体LLM团队重要？
When Does Personality Composition Matter for Multi-Agent LLM Teams?
AI总结：
研究通过操纵前沿LLM的人格特质，发现人格对多智能体团队性能的影响取决于任务结构：在编码任务中影响小，在开放协作和谈判任务中显著降低性能。
摘要：
人格提示塑造了大型语言模型的交流方式，但这些行为转变是否影响客观任务结果仍未充分探索。先前研究表明，被提示低宜人性的智能体产生对抗性语言，而被提示高宜人性的智能体变得合作，但交流风格与任务表现之间的关系尚未在多个领域进行系统检验。在这项工作中，我们通过在前沿LLM上操纵人格特质，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）研究人格构成是否对多智能体团队性能重要。我们发现人格效应关键取决于任务结构。在编码任务中，低宜人性导致大的交流转变，但对里程碑完成影响甚微。在开放式协作和谈判中，相同的操纵显著降低了性能。我们讨论了对多智能体系统设计的影响以及人格操纵的局限性。
英文摘要：
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.
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。
