LLM 增强的网络社交智能体仿真研究
LLM-Augmented Agent-Based Simulation of Cyber Social Agents
AI 导读
一项 arXiv 研究提出“网络社交智能体”（Cyber Social Agents）概念，按操作策略和修辞风格对社交媒体自动化角色进行分类，并融入 LLM 驱动的社交仿真，让智能体在网络环境中通信与协调。研究基于经验数据构建智能体角色，模拟异质化在线社会，分析智能体多样性如何影响信息扩散与社会影响力。
正文 · 原文
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.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2610.32988 [cs.MA] |
| (or arXiv:2610.32988v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32988 arXiv-issued DOI via DataCite |
Submission history
From: Lynnette Hui Xian Ng [view email]
[v1]
Sat, 22 Aug 2026 12:43:36 UTC (1,963 KB)
来源：arXiv cs.AI · arxiv.org