VirtLab: An AI-Powered System for Flexible, Customizable, and Large-scale Team Simulations

2025-08-06

AI Summary

Existing team simulation frameworks lack support for flexible scenario definition and spatial modeling, hindering accurate representation of collaborative dynamics in complex environments. This paper introduces an LLM-based multi-agent team simulation system that integrates Agentic AI, a spatiotemporal-aware simulation engine, and a low-code web visualization interface—enabling non-programmers to define custom collaboration scenarios and spatial topologies. Individual agent decisions and interactions are modeled via LLMs grounded in spatiotemporal context, enabling high-fidelity simulation of emergent team behaviors. Empirical evaluation replicates and benchmarks against real-world team data across diverse collaborative tasks, demonstrating strong validity and simulation accuracy. The framework overcomes key limitations of prior approaches in flexibility, scalability, and usability, providing a transparent, reproducible, and interpretable computational experimentation platform for hypothesis testing in the social sciences. (149 words)

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Teamwork, Team formation
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Simulating how team members collaborate within complex environments using Agentic AI is a promising approach to explore hypotheses grounded in social science theories and study team behaviors. We introduce VirtLab, a user-friendly, customizable, multi-agent, and scalable team simulation system that enables testing teams with LLM-based agents in spatial and temporal settings. This system addresses the current frameworks' design and technical limitations that do not consider flexible simulation scenarios and spatial settings. VirtLab contains a simulation engine and a web interface that enables both technical and non-technical users to formulate, run, and analyze team simulations without programming. We demonstrate the system's utility by comparing ground truth data with simulated scenarios.

Problem

• Simulating team collaboration in complex environments using AI
• Addressing limitations in flexible simulation scenarios and spatial settings
• Enabling user-friendly team simulation without programming requirements

Innovation

• AI-powered multi-agent team simulation system
• Customizable spatial and temporal settings
• User-friendly web interface for simulations