预测智能体社会中社会机制的规模极限

AI 摘要

该研究提出了一种审计方法，用于预测语言模型智能体社会中社会机制（如互惠、共识、惩罚、八卦）随群体规模扩大时的存续情况。通过控制实验发现，单一结构项可决定机制是否随规模扩展而存续，且智能体对信息的表达形式（如计数与百分比）敏感。预测在第三方代码和另一模型家族上得到验证，失败案例揭示了方法的边界。该审计为跨规模解释社会机制提供了前瞻性工具。

正文节选

Predicting the scale limits of social mechanisms in agent societies Abstract Societies of interacting language-model agents offer a controllable and repeatable way to study collective behaviour at scales that would be difficult to test with people. Their scientific value, however, depends on whether a social mechanism that works in a small group still operates when thousands of agents interact, and testing this directly requires costly large-scale runs. Here we introduce an audit that predicts a

发布时间：2026-08-25 12:00

抓取时间：2026-08-25 12:51

来源机构：arXiv