paper-with-me

홈 › Papers

On the Fragility of AI Agent Collusion

2026-03-18 · Jussi Keppo, Yuze Li, Gerry Tsoukalas, Nuo Yuan arxiv

Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity.

📄 PDF Abstract BibTeX arXiv:2603.20281

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

2026-02-16 · Mason Nakamura, Abhinav Kumar, Saswat Das, Sahar Abdelnabi 외 arxiv

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a …

Emergent Collusion in Long-Horizon LLM Agent Interaction

2026-09-21 · Xinrui Shi, Yanzhe Zhang, Diyi Yang hf

LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emergence of collusion in a long-horizon multi-agent environment: two agen…

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

2026-04-01 · Aaron Rose, Carissa Cullen, Sahar Abdelnabi, Philip Torr 외 arxiv

As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise fo…

Anomaly Detection

Voluntary Collusion with Secret Tools in Competing LLM Agents

2026-05-26 · Xijie Zeng, Frank Rudzicz arxiv

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate …

"Guinea Pig Trials" Utilizing GPT: A Novel Smart Agent-Based Modeling Approach for Studying Firm Competition and Collusion

2023-08-21 · Xu Han, Zengqing Wu, Chuan Xiao

Firm competition and collusion involve complex dynamics, particularly when considering communication among firms. Such issues can be modeled as problems of complex systems, traditionally approached through experiments in…

Decision Making