Large language models (LLMs) have been widely used as agents to complete different tasks, such as personal assistance or event planning. While most work has focused on cooperation and collaboration between agents, little work explores competition, another important mechanism that fosters the development of society and economy. In this paper, we seek to examine the competition behaviors in LLM-based agents. We first propose a general framework to study the competition between agents. Then, we implement a practical competitive environment using GPT-4 to simulate a virtual town with two types of agents, including restaurant agents and customer agents. Specifically, restaurant agents compete with each other to attract more customers, where the competition fosters them to transform, such as cultivating new operating strategies. The results of our experiments reveal several interesting findings ranging from social learning to Matthew Effect, which aligns well with existing sociological and economic theories. We believe that competition between agents deserves further investigation to help us understand society better. The code will be released soon.

翻译：大语言模型（LLMs）已被广泛用作智能体以完成各类任务，例如个人助理或活动规划。尽管现有工作多聚焦于智能体间的合作与协作，但鲜有研究探索竞争这一驱动社会与经济发展的重要机制。本文旨在考察基于LLM的智能体中的竞争行为。我们首先提出一个通用框架用于研究智能体间的竞争，随后利用GPT-4实现了一个实用的竞争环境，模拟了一个包含两类智能体（餐厅智能体与顾客智能体）的虚拟城镇。具体而言，餐厅智能体通过相互竞争以吸引更多顾客，这一竞争促使它们发生转变，例如制定新的运营策略。实验结果揭示了从社会学习到马太效应等多个有趣发现，这些发现与现有社会学及经济学理论高度吻合。我们认为，智能体间的竞争机制值得进一步研究以深化对社会现象的理解。代码将于近期公开。