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

2026-04-20

AI Summary

This work addresses a critical limitation in current large language model (LLM)-based social simulations, which typically treat social networks as static communication scaffolds and thereby overlook the pivotal role of network topology in shaping behavioral convergence and heterogeneity, resulting in inefficient and unrealistic outcomes. To overcome this, we propose TopoSim, a novel framework that integrates graph-structured analysis with LLMs by aligning agents to structural roles to form cohesive backbone units and introducing a topology-guided mechanism for agent grouping and interaction that explicitly models structure-driven social influence. Evaluated across multiple datasets and simulation environments, TopoSim reduces token consumption by 50%–90% while more accurately reproducing the structural dynamics of real-world social systems, demonstrating high fidelity, strong generalizability, and scalability.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• social simulation
• large language models
• network topology
• agent dynamics
• structural influence

Innovation

• topology-aware simulation
• LLM-driven agents
• structural reasoning
• heterogeneous influence
• efficient social dynamics