自利代理社会中市场稳定性的形式机制：市场模拟研究
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
AI总结：
研究自利代理社会中市场稳定性的形式机制，通过多智能体市场模拟实验，比较八种机制，发现调解机制最佳，对其进行对抗性红队测试，结果表明该机制具有对抗鲁棒性，能在攻击下维持市场稳定。
摘要：
在重复的社会困境中，不受约束的自利代理往往会走向背叛，导致贸易合作收益崩溃。本文研究在不受限制的沟通之上，何种形式机制足以让这样的代理社会维持市场稳定性，以及这些机制对对抗性攻击的弹性如何。通过多智能体市场模拟实验，在200轮渐进式恶意注入下比较八种机制，发现调解机制表现最佳。对调解机制进行对抗性红队测试，最佳攻击使诚实代理效用降低13.3%但未使市场崩溃，调解机制具有对抗鲁棒性。
英文摘要：
Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain market stability, and how resilient those mechanisms are to adversarial attack. We instantiate the research question as a multi-agent marketplace simulation where 18 LLM agents (DeepSeek-V3) with complementary production specialties must trade within a constrained social network to obtain utility. We conduct two experimental phases: (1) a mechanism comparison across eight conditions under progressive troll injection over 200 rounds, identifying Mediation as the top-performing mechanism; and (2) adversarial red-teaming of Mediation using iteratively prompt-optimised LLM-driven trolls, finding that the best attack (v6) reduces honest-agent utility by 13.3% but cannot collapse the market. Mediation enables recovery even under sustained adversarial pressure. We define adversarial robustness as a mechanism's ability to sustain positive honest-agent utility under optimised attack, and find that Mediation is robust: it can be bent but not broken.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
