Federated Experiments: Generative Causal Inference Powered by LLM-Based Agents Simulation and RAG-Based Domain Docking

Deyu Zhou, Xiao Xue, Qun Ma, Chao Guo, Li-Zhen Cui, Yonglin Tian, Jing Yang, Fei-Yue Wang

Abstract: Computational experiments method is an essential tool for analyzing, designing, managing, and integrating complex systems. However, a significant challenge arises in constructing agents with human-like characteristics to form an AI society. Agent modeling typically encompasses four levels: 1) The autonomy features of agents, e.g., perception, behavior, and decision-making; 2) The evolutionary features of agents, e.g., bounded rationality, heterogeneity, and learning evolution; 3) The social features of agents, e.g., interaction, cooperation, and competition; 4) The emergent features of agents, e.g., gaming with environments or regulatory strategies. Traditional modeling techniques primarily derive from ABMs (Agent-based Models) and incorporate various emerging technologies (e.g., machine learning, big data, and social networks), which can enhance modeling capabilities, while amplifying the complexity [1].