Coupling Macro Dynamics and Micro States for Long-Horizon Social Simulation

TL;DR

This paper introduces MF-MDP, a novel social simulation framework that couples macro-level collective opinion dynamics with micro-level individual states, enabling more accurate long-horizon social modeling.

Contribution

MF-MDP explicitly models individual latent opinion states with a transition mechanism, improving long-term simulation accuracy and capturing opinion reversals.

Findings

Supports stable simulation of up to 40,000 interactions

Reduces long-horizon KL divergence by 75.3%

Reduces reversal KL by 66.9%

Abstract

Social network simulation aims to model collective opinion dynamics in large populations, but existing LLM-based simulators mainly focus on aggregate dynamics while largely ignoring individual internal states. This limits their ability to capture opinion reversals driven by gradual individual shifts and makes them unreliable in long-horizon simulations. We propose MF-MDP, a social simulation framework that tightly couples macro-level collective dynamics with micro-level individual states. MF-MDP explicitly models per-agent latent opinion states with a state transition mechanism, combining individual Markov Decision Processes at the micro level with a mean-field collective framework at the macro level. This allows individual behaviors to change internal states gradually rather than trigger instant reactions, enabling the simulator to distinguish agents that are close to switching from those that are far from switching, capture opinion reversals, and maintain accuracy over long horizons. Across real-world events, MF-MDP supports stable simulation of long-horizon social processes with up to 40,000 interactions, compared with about 300 in the baseline MF-LLM, while reducing long-horizon KL divergence by 75.3% (1.2490 to 0.3089) and reversal KL by 66.9% (1.6425 to 0.5434), significantly mitigating the drift observed in MF-LLM. Code is available at github.com/AI4SS/MF-MDP.