Search papers, labs, and topics across Lattice.
This paper introduces Eco3S, a novel agent-based modeling framework designed to enhance socio-economic system simulations by addressing key challenges in agent-environment interactions, counterfactual reasoning, and simulation workflows. The framework incorporates three innovative mechanisms: Co-evolving Environment Design for realistic emergent behaviors, Structural Causal Simulation for flexible causal inference, and a Simulation-Analysis-Refinement Paradigm for iterative experimental design improvements. Experimental results confirm Eco3S's effectiveness in replicating established economic studies and demonstrate its scalability and generalizability for rigorous economic research and policy analysis.
Eco3S can replicate complex economic phenomena while allowing for flexible interventions and iterative refinement, setting a new standard for agent-based modeling in socio-economic research.
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.
