多智能体系统中涌现的歧视与极化
原标题：Emergent Discrimination and Polarization in Multi-Agent Systems
AI 摘要
该研究从理论上探讨学习型智能体群体中歧视与极化如何涌现。每个智能体用自适应线性决策层将语言模型嵌入映射为二元观点，并维护对其他智能体的信任估计，通过基于贝叶斯规则的成对交互更新权重与信任；大语言模型的上下文学习实验定性复现了预测的观点与信任更新。作者为智能体分配任意群体标签并引入偏见强度，利用统计力学序参量发现四种集体状态：无歧视极化、有观点对齐的歧视、无观点对齐的歧视以及外群体偏好的挫败态，具体状态取决于偏见的强度与普遍程度。研究强调多智能体系统需要群体层面的安全分析。
正文节选
Emergent Discrimination and Polarization in Multi-Agent Systems Abstract We study theoretically how discrimination and polarization can emerge in a population of learning agents. Each agent uses an adaptive linear decision layer to map a language-model embedding of an issue to a binary opinion and maintains an evolving estimate of how much it trusts every other agent. Through pairwise interactions, agents update both their decision weights and trust estimates using an online Bayesian rule deriv