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

Edoardo Allegrini, Edoardo Di Paolo, Angelo Spognardi, Marinella Petrocchi
3/31/2026
cs.SIcs.AIcs.MA

No official code found. Best implementation: netsecuritylab/BotVerse (3 stars, MIT, last commit 2026-04-09).

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.

View on arXivView PDF

Code Implementations(1)

netsecuritylab/BotVerseCommunity72%
MIT

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

30CSS, PythonMar 3, 20266 months agoMIT

Similar Papers

Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs

86% match2025

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents

85% match2025

Large Population Models

85% match1 repo6502025

MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming

85% match2023

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

85% match2026

Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges

85% match2025

Cite this paper

@article{allegrini2026botverse,
  title  = {BotVerse: Real-Time Event-Driven Simulation of Social Agents},
  author = {Edoardo Allegrini and Edoardo Di Paolo and Angelo Spognardi and Marinella Petrocchi},
  year   = {2026},
  eprint = {2603.29741},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.29741v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.29741.svg)](https://codeofpaper.com/paper/2603.29741)

Discussion