通过拍卖实验研究大模型代理的个性如何影响竞争行为
HARBOR: Exploring Persona Dynamics in Multi-Agent Competition
- 给代理设定不同性格特征，模拟真实购房竞拍场景
- 发现性格差异显著影响出价策略和竞拍成功率
- 适合对多智能体博弈与心理建模感兴趣的读者
我们研究了大语言模型代理在竞争性多智能体环境中的成功因素，以拍卖为测试场景，代理需出价最大化利润。代理具备竞拍领域知识、反映物品偏好的独特人格，以及拍卖历史记忆。本工作扩展了经典拍卖场景，构建了一个现实环境，多个代理竞拍房屋，权衡面积、位置、预算等要素以最低价格获取理想房源。重点探究三个问题：(a) 人格如何影响代理在竞争环境中的行为？(b) 代理能否有效分析对手行为？(c) 如何利用人格分析，结合心理理论等策略获得优势。通过一系列实验，分析了大语言模型代理的行为模式，揭示新发现。所提出的测试平台HARBOR，为深入理解竞争环境中多智能体协作流程提供了重要平台。
原文摘要 · Abstract (English)
We investigate factors contributing to LLM agents' success in competitive multi-agent environments, using auctions as a testbed where agents bid to maximize profit. The agents are equipped with bidding domain knowledge, distinct personas that reflect item preferences, and a memory of auction history. Our work extends the classic auction scenario by creating a realistic environment where multiple agents bid on houses, weighing aspects such as size, location, and budget to secure the most desirable homes at the lowest prices. Particularly, we investigate three key questions: (a) How does a persona influence an agent's behavior in a competitive setting? (b) Can an agent effectively profile its competitors' behavior during auctions? (c) How can persona profiling be leveraged to create an advantage using strategies such as theory of mind? Through a series of experiments, we analyze the behaviors of LLM agents and shed light on new findings. Our testbed, called HARBOR, offers a valuable platform for deepening our understanding of multi-agent workflows in competitive environments.
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。