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

Xu Han, Zengqing Wu+1 more|arXiv (Cornell University)|Aug 21, 2023

Auction Theory and ApplicationsDecision Sciences被引用 3

一句话总结

本文提出了一种新型框架——智能代理建模（SABM），利用GPT-4驱动的智能代理模拟企业间的竞争与合谋行为。与传统代理模型不同，SABM中的代理展现出类人的战略推理与沟通能力，从而能够真实模拟市场动态。主要发现为：沟通可加速合谋形成，并使价格趋近卡特尔水平；而无沟通时则形成价格高于古诺-伯特兰均衡但低于垄断水平的隐性合谋。

ABSTRACT

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 involving human subjects or agent-based modeling methods. We propose an innovative framework called Smart Agent-Based Modeling (SABM), wherein smart agents, supported by GPT-4 technologies, represent firms, and interact with one another. We conducted a controlled experiment to study firm price competition and collusion behaviors under various conditions. SABM is more cost-effective and flexible compared to conducting experiments with human subjects. Smart agents possess an extensive knowledge base for decision-making and exhibit human-like strategic abilities, surpassing traditional ABM agents. Furthermore, smart agents can simulate human conversation and be personalized, making them ideal for studying complex situations involving communication. Our results demonstrate that, in the absence of communication, smart agents consistently reach tacit collusion, leading to prices converging at levels higher than the Bertrand equilibrium price but lower than monopoly or cartel prices. When communication is allowed, smart agents achieve a higher-level collusion with prices close to cartel prices. Collusion forms more quickly with communication, while price convergence is smoother without it. These results indicate that communication enhances trust between firms, encouraging frequent small price deviations to explore opportunities for a higher-level win-win situation and reducing the likelihood of triggering a price war. We also assigned different personas to firms to analyze behavioral differences and tested variant models under diverse market structures. The findings showcase the effectiveness and robustness of SABM and provide intriguing insights into competition and collusion.

研究动机与目标

• 开发一种可扩展、成本效益高的替代方案，以替代人类被试实验，用于研究企业竞争与合谋行为。
• 通过引入大型语言模型赋予代理高级推理与沟通能力，解决传统代理模型的局限性。
• 研究沟通如何影响寡头市场中合谋的形成、价格收敛与战略行为。
• 通过模拟代理研究企业身份特征与市场结构对合谋动态的影响。

提出的方法

• SABM采用GPT-4作为每个企业代理的认知引擎，支持复杂决策与自然语言交互。
• 代理被赋予知识库与战略推理能力，以模拟现实中企业在定价与合谋决策中的行为。
• 模型在不同条件下模拟企业间的重复互动：包括有沟通与无沟通，以及不同市场结构。
• 代理参与价格设定博弈，结果被记录以分析收敛模式与合谋稳定性。
• 为代理分配身份特征，以模拟企业行为的异质性，如激进型与合作型。
• 通过受控模拟验证该框架，对比有沟通与无沟通场景下的结果。

实验结果

研究问题

• RQ1 企业在竞争市场中是否存在沟通，如何影响合谋形成的速率与稳定性？
• RQ2 GPT驱动的智能代理在寡头定价博弈中在多大程度上能复现类人的战略行为？
• RQ3 企业特定身份特征对模拟市场中合谋动态与定价结果有何影响？
• RQ4 不同市场结构如何影响SABM框架中合谋的出现与可持续性？
• RQ5 SABM在受控条件下能否复现已知的经济均衡，如伯特兰均衡与卡特尔定价？

主要发现

• 在无沟通情况下，智能代理始终实现隐性合谋，价格收敛至高于伯特兰均衡但低于垄断价格的水平。
• 当启用沟通后，代理形成更高水平的合谋，实现接近卡特尔均衡水平的价格。
• 沟通显著加速了合谋的形成，相较于无沟通场景，价格收敛时间大幅缩短。
• 在有沟通的情况下，代理表现出更频繁的小幅价格偏离，表明其更积极地探索更高双赢结果，并降低了价格战风险。
• 引入不同企业身份特征后，可观察到行为差异，其中更具合作性的代理有助于实现更快、更稳定的合谋。
• SABM框架在多种市场结构下表现出强健性，证实其作为人类被试实验可扩展替代方案的可行性。