Topology-Aware LLM-Driven Social Simulation: A Unified Framework for Efficient and Realistic Agent Dynamics

TL;DR

TopoSim is a topology-aware social simulation framework that enhances realism and efficiency by integrating structural signals into agent interactions, reducing computation and better modeling real-world social phenomena.

Contribution

It introduces a unified approach that explicitly incorporates social network topology into LLM-driven simulations, improving fidelity and efficiency.

Findings

Achieves 50-90% reduction in token consumption.

Better reproduces structural phenomena in social systems.

Maintains or improves simulation fidelity.

Abstract

Social simulation is essential for understanding collective human behavior by modeling how individual interactions give rise to large-scale social dynamics. Recent advances in large language models (LLMs) have enabled multi-agent frameworks with human-like reasoning and communication capabilities. However, existing LLM-based simulations treat social networks as fixed communication scaffolds, failing to leverage the structural signals that shape behavioral convergence and heterogeneous influence in real-world systems, which often leads to inefficient and unrealistic dynamics. To address this challenge, we propose TopoSim, a unified topology-aware social simulation framework that explicitly integrates structural reasoning into agent interactions along two complementary dimensions. First, TopoSim aligns agents with similar structural roles and interaction contexts into shared backbone units, enabling coordinated updates that reduce redundant computation while preserving emergent social dynamics. Second, TopoSim models social influence as a structure-induced signal, introducing heterogeneous interaction patterns grounded in network topology rather than uniform influence assumptions. Extensive experiments across three social simulation frameworks and diverse datasets demonstrate that TopoSim achieves comparable or improved simulation fidelity while reducing token consumption by 50 - 90%. Moreover, our approach more accurately reproduces key structural phenomena observed in real-world social systems and exhibits strong generalization and scalability.