SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation
This addresses the challenge of simulating nuanced, long-term social dynamics for researchers in computational social science, representing a novel method rather than an incremental improvement.
The paper tackles the problem of limited temporal stability in agent-based modeling of social systems by introducing SALM, a multi-agent framework that integrates language models into social network simulation, achieving stable simulation beyond 4,000 timesteps with a 73% reduction in token usage and 80% cache hit rates.
Contemporary approaches to agent-based modeling (ABM) of social systems have traditionally emphasized rule-based behaviors, limiting their ability to capture nuanced dynamics by moving beyond predefined rules and leveraging contextual understanding from LMs of human social interaction. This paper presents SALM (Social Agent LM Framework), a novel approach for integrating language models (LMs) into social network simulation that achieves unprecedented temporal stability in multi-agent scenarios. Our primary contributions include: (1) a hierarchical prompting architecture enabling stable simulation beyond 4,000 timesteps while reducing token usage by 73%, (2) an attention-based memory system achieving 80% cache hit rates (95% CI [78%, 82%]) with sub-linear memory growth of 9.5%, and (3) formal bounds on personality stability. Through extensive validation against SNAP ego networks, we demonstrate the first LLM-based framework capable of modeling long-term social phenomena while maintaining empirically validated behavioral fidelity.