Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
For multi-agent systems and AI safety, this work demonstrates that a mediation mechanism can robustly sustain cooperation under optimised adversarial pressure, addressing the problem of defection in agent societies.
This paper investigates formal mechanisms for maintaining market stability in societies of self-interested LLM agents, finding that Mediation is the top-performing mechanism, enabling recovery under adversarial attack with only a 13.3% reduction in honest-agent utility without market collapse.
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.