BotVerse: Real-Time Event-Driven Simulation of Social Agents

TL;DR

BotVerse is a scalable, real-time social simulation framework using LLM agents, enabling safe, controlled experiments on social interactions and disinformation scenarios grounded in real content streams.

Contribution

It introduces a novel event-driven simulation system with real-time content integration and customizable personas for high-fidelity social agent research.

Findings

Demonstrated disinformation scenario simulation at scale

Provided a safe environment for studying autonomous social agents

Enabled multimodal interaction analysis

Abstract

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.