LLM 增强的网络社会智能体仿真
LLM-Augmented Agent-Based Simulation of Cyber Social Agents
Lynnette Hui Xian Ng · Kathleen M. Carley
中文摘要
社交媒体机器人常被视为应被检测和移除的恶意自动化程序，但平台上的自动化涵盖多种角色、行为与修辞策略，既可能建设性地塑造网络讨论，也可能造成破坏。研究以基于实证数据的网络社会智能体(Cyber Social Agents)角色原型分类体系刻画这些行动者，并将其纳入 LLM 驱动的社会仿真，使智能体在网络环境中交流与协作。借助基于实证数据构建的智能体角色，仿真多样化网络社会，分析智能体差异如何影响信息扩散与社会影响，从而在基于规则的智能体模型与由 LLM 驱动、参数源自实证数据的生成式智能体仿真之间建立联系。
关键要点
- 01将社交媒体自动化行动者概括为网络社会智能体
- 02按操作策略与修辞风格构建角色原型分类体系
- 03在网络环境中以 LLM 驱动智能体交流与协作
- 04利用基于实证数据的角色仿真异质网络社会
- 05分析智能体多样性对信息扩散和社会影响的作用
解读
尚无解读。
原始英文摘要
arXiv:2610.32988v1 Announce Type: cross Abstract: Social media bots are often portrayed as malicious automations to be detected and removed, but automation on social media platforms encompasses a wide spectrum of roles, behaviors, and rhetorical strategies that can shape online discourse in both constructive and destructive ways. This work conceptualizes these automated actors as \textbf{Cyber Social Agents} through a taxonomy of archetypes characterized by their operational tactics and rhetorical style. We integrate this taxonomy into an LLM-driven social simulation, where agents communicate and coordinate in a network environment. Using empirically grounded CSA personas, we simulate heterogeneous online societies to study how agent diversity shapes information diffusion and social influence. Our approach bridges the gap between rule-based agent models and LLM-powered simulations with generated agents that are parameterized from empirical data.