真实场景中AI代理因差异难串通，串通易破局。
On the Fragility of AI Agent Collusion
- 用异质性模拟真实部署，发现耐心与数据差异削弱串通可能。
- 实验显示串通导致价格上浮从22%降至7%，竞争者越多越难串通。
- 模型大小差异反助串通，适合关注算法监管的读者。
近期研究发现，对称的大型语言模型代理在定价中会引发算法串通。本文表明，在真实部署常见的异质性条件下，这种串通极为脆弱。在简化的重复定价模型中，耐心或数据访问的异质性会缩小串通均衡的范围。基于开源大模型代理（总计超过2000小时算力）的实验结果与预测一致：耐心异质性使价格上浮从22%降至10%；数据访问不对称则降至7%。增加竞争模型数量或引入异构算法（如将大模型与Q-learning代理对抗）可打破串通；但模型规模差异（如32B vs. 14B参数）反而形成领导者-追随者动态，稳定串通。文章讨论反垄断意义，建议限制数据共享并推动算法多样性政策。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。