TwinMarket：用于金融市场的可扩展行为和社交模拟系统

摘要

长期以来，社会出现研究一直是社会科学的中心关注点。传统建模方法，如基于规则的基于代理的模型（ABMs），难以捕捉人类行为的多样性和复杂性，特别是行为经济学强调的非理性因素。最近，大型语言模型（LLM）代理作为模拟工具在社会科学和角色扮演应用中得到了广泛应用，用于建模人类行为。研究表明，LLMs可以考虑认知偏见、情绪波动和其他非理性影响，从而实现对社会经济动态更真实的模拟。在这项工作中，我们介绍了TwinMarket，这是一个利用LLMs来模拟社会经济系统的新型多代理框架。具体而言，我们研究了个体行为如何通过相互作用和反馈机制导致集体动态和 emergent 现象的产生。通过在模拟股票市场环境中进行实验，我们展示了个体行为如何引发群体行为，导致 emergent 结果，如金融泡沫和经济衰退。我们的方法为个体决策与集体社会经济模式之间复杂相互作用提供了宝贵的见解。

English

The study of social emergence has long been a central focus in social science. Traditional modeling approaches, such as rule-based Agent-Based Models (ABMs), struggle to capture the diversity and complexity of human behavior, particularly the irrational factors emphasized in behavioral economics. Recently, large language model (LLM) agents have gained traction as simulation tools for modeling human behavior in social science and role-playing applications. Studies suggest that LLMs can account for cognitive biases, emotional fluctuations, and other non-rational influences, enabling more realistic simulations of socio-economic dynamics. In this work, we introduce TwinMarket, a novel multi-agent framework that leverages LLMs to simulate socio-economic systems. Specifically, we examine how individual behaviors, through interactions and feedback mechanisms, give rise to collective dynamics and emergent phenomena. Through experiments in a simulated stock market environment, we demonstrate how individual actions can trigger group behaviors, leading to emergent outcomes such as financial bubbles and recessions. Our approach provides valuable insights into the complex interplay between individual decision-making and collective socio-economic patterns.

TwinMarket：用于金融市场的可扩展行为和社交模拟系统

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

摘要

Summary

Support