智能AI
morning
人格构成何时对多代理 LLM 团队很重要?
2026-06-29
1 阅读
Aryan Keluskar, Amrita Bhattacharjee, Huan Liu
arXiv:2606.27443v1 公告类型:新 摘要:个性提示决定大型语言模型的沟通方式,但这些行为转变是否影响客观任务结果仍有待探索。先前的研究表明,低宜人性提示的智能体会产生对抗性语言,而高宜人性提示的智能体会变得合作,但沟通方式与任务绩效之间的关系尚未在多个领域进行系统地检验。在这项工作中,我们通过在结构化编码、开放式研究合作和竞争性谈判这三个任务领域操纵前沿法学硕士的人格特质,研究人格构成是否对多智能体团队绩效重要。 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.