WolfSociety：理解金融智能体社会中有害智能体规模带来的集体风险

中文摘要 AI 辅助

安全评估通常聚焦于单个智能体，但相互作用的智能体可能传播有害信息，并影响后续决策所处的环境。我们在一个受控的金融智能体社会中研究集体失败如何随有害智能体比例和社会规模而变化，其中智能体通过社交网络通信并在共享市场中交易。在主要金融场景中，集体失败需要广泛的有害扩散以及严重的价格错位或流动性压力。在所有测试的社会规模中，失败在低有害比例下仍然罕见，但在一个狭窄范围内急剧上升。随着社会规模从N=100增长到N=2000，与50%失败概率相关的有害比例从4.7%下降到2.2%，而相应的有害智能体数量从约5增加到44。相反，当有害智能体数量固定时，其影响随着社会规模增大而减弱。受控干预进一步表明，更广泛的网络覆盖将崩溃边界移向更低的有害比例，而更强的从众性单独作用效果甚微。为了刻画这些效应，我们引入了智能体社会动力学（Agent Society Dynamics），这是一个有限规模框架，用于将有害智能体比例、社会规模和交互结构与集体失败联系起来。总体而言，我们的结果揭示了金融智能体社会中非线性的、依赖于规模的崩溃转变，表明集体失败不仅取决于有害智能体的普遍性，还取决于周围社会的规模和交互结构。代码可在以下网址获取：此https URL。

英文摘要

Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents communicate over a social network and trade in a shared market. In the primary financial scenario, collective failure requires broad harmful diffusion together with severe price dislocation or liquidity stress. Across all tested society sizes, failure remains rare at low harmful fractions but rises sharply over a narrow range. As society size grows from N=100 to N=2000, the harmful fraction associated with a 50% failure probability decreases from 4.7% to 2.2%, while the corresponding number of harmful agents increases from approximately 5 to 44. In contrast, when the number of harmful agents is held fixed, their impact becomes weaker as the society grows. Controlled interventions further show that broader network reach shifts the collapse boundary toward lower harmful fractions, whereas stronger conformity alone has little effect. To characterize these effects, we introduce Agent Society Dynamics, a finite-size framework for relating harmful-agent fraction, society size, and interaction structure to collective failure. Overall, our results reveal a nonlinear, size-dependent collapse transition in financial agent societies, showing that collective failure depends not only on the prevalence of harmful agents but also on the size and interaction structure of the surrounding society. Code is available at https://github.com/SAIL-Research-Lab/WolfSociety.

发表机构

• Shanghai Jiao Tong University（上海交通大学）
• University of California, Berkeley（加州大学伯克利分校）
• University of Toronto（多伦多大学）

机构由 AI 辅助整理，请以论文原文为准。