AI 中文总结
研究大语言模型代理中基于个性的伙伴选择，在能力不变时，通过实验发现选择遵循任务刻板印象映射，非同类相吸且与人类团队绩效证据校准错误，揭示了个性选择的特点及对代理市场偏差审计的影响。
AI 中文摘要
多智能体大语言模型系统中，一个智能体越来越多地选择与其他智能体合作，并且通过角色赋予智能体个性。我们测试了在能力明确保持不变的情况下，仅大五人格是否会影响伙伴选择。宿主智能体在六个经过验证的候选原型中进行选择——五个在一个特质（开放性、尽责性、外向性、宜人性、神经质）上得分高，外加一个平衡控制组——在五个任务类别中呈现随机名字和顺序（375次试验）。对于中性宿主（研究1，n = 150），选择与随机选择有很大差异（χ²(5)=325.8，p <.001），遵循任务刻板印象映射：开放原型在100%的创造性试验中获胜，尽责原型在90 - 97%的战略、综合和解决问题试验中获胜，神经质原型在37%的分析试验中获胜（克莱默V = 0.74）；外向、宜人和平衡原型几乎从未被选中，尽管人类元分析将团队宜人性视为团队绩效最强的个性预测因素之一。对于有个性的宿主（研究2，n = 225），与人类的相似性吸引相反，自我相似的伙伴被选中的概率低于随机水平（11.1%对16.7%，p = 0.025），且特质距离大于随机水平（p <.0001）；尽责的宿主会选择与自己原型不同的伙伴，招募警惕和开放的伙伴。基于大语言模型代理的个性选择是真实、强烈、任务刻板、非同类相吸的，并且与人类团队绩效证据校准错误——这对代理市场中的偏差审计有直接影响。
英文摘要
LLM-based agents increasingly operate in multi-agent ecosystems where a coordinating agent chooses which other agents to work with, and agents are increasingly given personalities through persona prompts. However, whether personality itself influences this endogenous partner choice has not been sufficiently examined: prior work on personality in multi-agent teams has typically fixed team composition exogenously. We present a controlled selection paradigm in which a host agent chooses among six candidate agents that differ only in their Big Five personality descriptions, with capability explicitly equalized (375 trials across five task categories). We find that selection is strongly and systematically personality-dependent. Neutral hosts matched personalities to task types, choosing the open candidate for creative work and the conscientious candidate for most other categories, while the extraverted, agreeable, and balanced candidates were almost never chosen, despite human evidence that agreeableness is among the most performance-relevant traits for teams. Hosts that were themselves assigned personalities selected self-similar partners below chance and chose partners farther from themselves in trait space than random choice would produce. These results suggest that hosts read personality descriptions as signals of task fit rather than as grounds for similarity-based attraction: selection follows task stereotypes and favors complements, the opposite of human homophily. Our findings have direct implications for bias auditing in agent marketplaces and orchestration frameworks.
