用大模型驱动社交网络模拟，实现超长时稳定且高效的行为建模。
SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation
- 分层提示架构让模拟稳定超过4000步，节省73%生成令牌
- 注意力记忆系统缓存命中率达80%，内存增长仅9.5%的亚线性水平
- 首次给出人格稳定性理论边界，适合研究长期社交演化者
当前基于代理的社交系统建模多依赖预设规则，难以捕捉复杂社会互动。本文提出SALM（Social Agent LM Framework），将语言模型融入社交网络模拟，首次实现多代理场景下超长时程稳定。核心贡献包括：(1) 分层提示架构使模拟时间超过4000步，同时减少73%的令牌消耗；(2) 基于注意力的记忆系统达到80%缓存命中率（95%置信区间[78%, 82%]），内存增长仅为9.5%的亚线性水平；(3) 建立人格稳定性的形式化边界。在SNAP ego网络上的实证验证表明，该框架是首个能长期模拟社会现象并保持行为真实性的大模型驱动方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。