Jul 29, 2026 · cs.AIJ/K move · Enter open · S save
Shaopeng Wei, Yufei Cheng, Wenxi Sun, Yepeng Ding+2
School of Business, Guangxi University, Nanning 530004, China · School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 611130, China · Information Media Center, Hiroshima University, Hiroshima 739-8511, Japan · Business Administration, Faculty of Business Administration, Southwestern University of Finance and Economics, Chengdu 611130, China
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.