发表机构
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过实验比较三种监管干预措施，发现改变激励或市场参与度（如Harrington监管器和主动随机进入者）比仅提示警告更能有效缓解LLM定价智能体的涌现性合谋，降低超竞争性定价。
AI 中文摘要
近期研究表明，基于大语言模型的定价智能体在重复寡头竞争环境中，即使未被明确指示合谋，也能产生超竞争性结果。我们使用DeepSeek-V3.1复现了Fish等人的定性提示敏感性效应：P1提示产生的价格和利润显著高于P2，尽管我们的结果比原始GPT-4结果更少垄断特征。随后，我们评估了三种监管干预措施：仅提示警告、受Harrington启发的预期损害收益监管器，以及主动随机进入者。仅提示警告的监管器减少了但未消除高于纳什均衡的定价。Harrington监管器使P1结果接近双寡头纳什基准，并消除了统计显著的P1-P2差距。主动随机进入者产生了最强效果，将两种提示均推至低于相应的随机进入者纳什基准。总体而言，我们的实验提供了初步证据，表明改变激励或市场参与度的干预措施比仅提示警告更能有效减少超竞争性定价。
英文摘要
Recent work shows that LLM-based pricing agents can produce supracompetitive outcomes in repeated oligopoly environments without being explicitly instructed to collude. We reproduce the qualitative prompt-sensitivity effect of Fish et al. using DeepSeek-V3.1: the P1 prompt produces significantly higher prices and profits than P2, although our outcomes are less monopoly-like than the original GPT-4 results. We then evaluate three regulatory interventions: a prompt-only warning, a Harrington-inspired expected-damages payoff regulator, and an active random entrant. The prompt-only regulator reduces but does not eliminate above-Nash pricing. The Harrington regulator brings P1 outcomes close to the duopoly Nash benchmark and removes the statistically significant P1--P2 gap. The active entrant produces the strongest effect, pushing both prompts below the appropriate random-entrant Nash benchmark. Overall, our experiments provide preliminary evidence that interventions that alter incentives or market participation can reduce supracompetitive pricing more effectively than prompt warnings alone.
