Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model

2026-08-01

AI Summary

This study investigates how collective influence, narrative dominance, and coordinated behavior emerge from individual interactions within communication networks. To this end, we introduce AuraSight, a multi-agent network dynamics simulation framework integrating large language models within the GhostField architecture. AuraSight combines heterogeneous agent modeling, dynamic network evolution, semantic network analysis, and multilayer social simulation to model over 310,000 agents interacting over 30 days around a fictional international songwriting contest. The experiments successfully reproduce key features of real-world social dynamics and demonstrate, for the first time, that collective coordination and influence arise not from individual intelligence but from the recursive interplay between network topology and narrative exchange, thereby establishing a novel paradigm for large-scale social simulation.

Abstract

Social dynamics encode the process in which individual network and discourse interactions aggregate into collective influence, narrative dominance and coordinate behavior. This paper uses the the GhostField architecture, a hybrid LLM-Enabled Agent Based Network-Dynamic (LAND) model as a social simulation framework to build the AuraSight scenario. In the AuraSight scenario, 314,244 heterogeneous cyber social agents and human actors exchange 529,327 messages over 30 days surrounding a fictional international song-writing contest. We methodologically examine emergent social dynamics across four analytical layers: ego-network topology, semantic network evolution, coordination dynamics and influence dynamics. Our results show how generated social simulations do also produce social dynamics, and how the dynamics of coordination and influence emerge not from individual agents but from the recursive interaction between network topology and narrative exchange.

Problem

• social dynamics
• collective influence
• narrative dominance
• coordination behavior
• agent-based modeling

Innovation

• LLM-Enabled Agent-Based Modeling
• Social Dynamics
• Network-Dynamic Simulation
• Emergent Coordination
• Narrative Exchange