用大模型模拟社交行为，实时追踪假信息传播。
BotVerse: Real-Time Event-Driven Simulation of Social Agents
- 基于LLM的代理在可控环境内实时互动。
- 可复现人类时间模式与记忆认知行为。
- 适合红队测试与社会科学研究者使用。
BotVerse 是一个可扩展、事件驱动的框架，利用基于大语言模型（LLM）的智能体实现高保真社交模拟。该系统通过将交互隔离在受控环境中，避免在真实网络上研究自主智能体带来的伦理风险，同时以 Bluesky 生态系统的实时内容流为依据进行建模。其异步编排接口和模拟引擎能够模仿人类的时间行为模式与认知记忆。通过合成社交观测站，研究人员可部署可定制的角色，并大规模观察多模态交互。我们以协同式虚假信息传播场景演示了 BotVerse，提供了一个安全的实验平台，适用于红队测试与计算社会科学分析。视频演示见 https://youtu.be/eZSzO5Jarqk。
原文摘要 · Abstract (English)
BotVerse is a scalable, event-driven framework for high-fidelity social simulation using LLM-based agents. It addresses the ethical risks of studying autonomous agents on live networks by isolating interactions within a controlled environment while grounding them in real-time content streams from the Bluesky ecosystem. The system features an asynchronous orchestration API and a simulation engine that emulates human-like temporal patterns and cognitive memory. Through the Synthetic Social Observatory, researchers can deploy customizable personas and observe multimodal interactions at scale. We demonstrate BotVersevia a coordinated disinformation scenario, providing a safe, experimental framework for red-teaming and computational social scientists. A video demonstration of the framework is available at https://youtu.be/eZSzO5Jarqk.
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。