Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study

Source

arXiv

arxiv.org/abs/2607.08652v1

Read the source

Source

Plain-Language Brief

The researchers investigated mechanisms that can maintain market stability in a society of self-interested agents who tend to defect in repeated social dilemmas. They conducted a multi-agent marketplace simulation with 18 LLM agents and compared eight conditions under progressive troll injection over 200 rounds. The top-performing mechanism was Mediation, which could recover even under sustained adversarial pressure. The study defined adversarial robustness as a mechanism's ability to sustain positive honest-agent utility under optimised attack, and found that Mediation is robust.

What the Document Says

  • The researchers studied mechanisms for market stability in a society of self-interested agents who tend to defect in repeated social dilemmas.
  • They conducted a multi-agent marketplace simulation with 18 LLM agents.
  • The study compared eight conditions under progressive troll injection over 200 rounds.
  • Mediation was found to be the top-performing mechanism.
  • Mediation could recover even under sustained adversarial pressure.
  • Adversarial robustness was defined as a mechanism's ability to sustain positive honest-agent utility under optimised attack.
  • The study found that Mediation is robust.

Key Concepts Mentioned

  • self-interested agents
  • market stability
  • social dilemmas
  • multi-agent marketplace simulation
  • LLM agents
  • Mediation
  • adversarial attack
  • adversarial robustness

Claims Made by the Document

  • Self-interested agents tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse.
  • The top-performing mechanism (Mediation) maintains market stability and can recover even under sustained adversarial pressure.
  • Adversarial robustness is a mechanism's ability to sustain positive honest-agent utility under optimised attack.

Evidence Used

  • The text describes the simulation experiment and its results.
  • The text defines terms such as 'adversarial robustness'.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.