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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Allegrini, Edoardo, Di Paolo, Edoardo, Spognardi, Angelo, Petrocchi, Marinella
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912992203898880
author Allegrini, Edoardo
Di Paolo, Edoardo
Spognardi, Angelo
Petrocchi, Marinella
author_facet Allegrini, Edoardo
Di Paolo, Edoardo
Spognardi, Angelo
Petrocchi, Marinella
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29741
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BotVerse: Real-Time Event-Driven Simulation of Social Agents
Allegrini, Edoardo
Di Paolo, Edoardo
Spognardi, Angelo
Petrocchi, Marinella
Social and Information Networks
Artificial Intelligence
Multiagent Systems
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.
title BotVerse: Real-Time Event-Driven Simulation of Social Agents
topic Social and Information Networks
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2603.29741