BotVerse: Real-Time Event-Driven Simulation of Social Agents
This provides a safe, experimental framework for computational social scientists and red-teaming to study autonomous agents without live network risks.
BotVerse introduces a scalable, event-driven framework for high-fidelity social simulation using LLM-based agents, addressing ethical risks by isolating interactions in a controlled environment grounded in real-time Bluesky content streams, and demonstrates it via a coordinated disinformation scenario for safe experimentation.
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.