AI 中文总结
Eco3S是面向经济研究与政策分析的社会经济系统仿真框架，通过三种关键机制解决现有LLM-based ABM的挑战，经多场景实验验证其有效性、可扩展性与通用性。
AI 中文摘要
大语言模型（LLMs）的快速发展重新激发了人们对基于智能体的建模（ABM）的兴趣。然而，当前基于LLM的ABM研究面临几个关键挑战：建模不断演变的智能体-环境交互、实现灵活的反事实推理，以及为科学研究自动化仿真工作流。在本文中，我们提出Eco3S，一个面向经济研究和政策分析的社会经济系统仿真框架，通过三种关键机制解决这些挑战：（1）协同演化环境设计，即智能体与环境协同演化的双向反馈循环，产生逼真的涌现行为；（2）结构因果仿真，一种受结构因果模型（SCM）启发的反事实机制，支持针对各类因果推理任务的灵活干预；（3）仿真-分析-优化范式，一种基于先前仿真结果迭代优化实验设计的自校正机制。在多种经济场景上的实验证实，Eco3S在复制多个已发表的经济研究（运河衰退、治理起源和信息传播）及跨领域现象方面的有效性，额外结果进一步证明其可扩展性和通用性，凸显该框架在严谨经济研究和政策制定中的潜力。
英文摘要
The rapid development of large language models (LLMs) has renewed interest in agent-based modeling (ABM). However, current LLM-based ABM research faces several key challenges: modeling evolving agent-environment interactions, enabling flexible counterfactual reasoning, and automating simulation workflows for scientific research. In this paper, we propose Eco3S, a socio-economic system simulation framework for economic research and policy analysis that addresses these challenges through three key mechanisms: (1) Co-evolving Environment Design, a bidirectional feedback loop where agents and the environment co-evolve, producing realistic emergent behaviors; (2) Structural Causal Simulation, a structural causal model (SCM)-inspired counterfactual mechanism that allows flexible interventions for diverse causal inference tasks; (3) Simulation-Analysis-Refinement Paradigm, a self-corrective mechanism that iteratively refines experimental designs based on prior simulation results. Experiments on diverse economic scenarios confirm \textit{Eco3S}'s effectiveness in replicating multiple established economic studies (canal decay, origins of governance, and information propagation) and phenomena across domains. Additional results further demonstrate its scalability and generalizability, highlighting the framework's potential for rigorous economic research and policy-making.
Comments18 pages, 18 figures, 7 tables
