利用LLM智能体研究模拟股票市场中的交易策略
文章 arXiv papers · 作者: Alejandro Lopez-Lira
总结
本文介绍一个模拟股票市场,其中大型语言模型作为相互竞争的智能体,具有不同的策略、信息和禀赋。市场包含持续运行的订单簿、市价单和限价单、部分成交、股息以及均衡撮合。智能体以结构化形式交流交易决策,同时也生成自然语言推理。在实验中,模型遵循了价值投资者、动量交易者或做市商等指定角色。模拟结果包括价格发现、泡沫、反应不足以及策略性流动性供给。
该框架旨在于无法进行闭式分析时研究金融理论和智能体行为,并开展成本高昂的人类参与者实验。它还可用于考察不同市场条件下的响应变化,以及共同提示词如何引发相关行为并影响稳定性。这些结果来自模拟:摘录并未显示LLM智能体能在实盘市场中稳定盈利,也未证明模拟动态能够完整复现真实市场。
核心观点
- 模拟交易所构建了包含市价单、限价单、部分成交、股息和撮合的订单簿。
- 在所述实验中,LLM智能体可以采用指定的价值投资、动量或做市策略。
- 模拟市场呈现了价格发现、泡沫、反应不足和流动性供给。
- 该框架支持研究缺乏闭式解的智能体行为和金融理论。
- 共同提示词引发的相关行为可能影响模拟市场的稳定性。
- 仅凭模拟结果不能证明实盘交易具有盈利能力。
标签
全文
# Can Large Language Models Trade? Testing Financial Theories with LLM Agents in Market Simulations # Can Large Language Models Trade? Testing Financial Theories with LLM Agents in Market Simulations This paper presents a realistic simulated stock market where large language models (LLMs) act as heterogeneous competing trading agents. The open-source framework incorporates a persistent order book with market and limit orders, partial fills, dividends, and equilibrium clearing alongside agents with varied strategies, information sets, and endowments. Agents submit standardized decisions using structured outputs and function calls while expressing their reasoning in natural language. Three findings emerge: First, LLMs demonstrate consistent strategy adherence and can function as value investors, momentum traders, or market makers per their instructions. Second, market dynamics exhibit features of real financial markets, including price discovery, bubbles, underreaction, and strategic liquidity provision. Third, the framework enables analysis of LLMs' responses to varying market conditions, similar to partial dependence plots in machine-learning interpretability. The framework allows simulating financial theories without closed-form solutions, creating experimental designs that would be costly with human participants, and establishing how prompts can generate correlated behaviors affecting market stability.
在遵守原作品许可的前提下,附作者信息全文展示。 许可协议: abstract CC0
此摘要由 Stratmill 研究智能体根据原文撰写,并非原文副本。