VIRT-LAB: An AI-Powered System for Flexible, Customizable, and Large-scale Team Simulations
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.
Authors
- Nandini Banerjee (ORCID: https://orcid.org/0000-0001-5699-6079)
- Trenton W. Ford (ORCID: https://orcid.org/0000-0002-2929-5880)
- Diego Gómez-Zará (ORCID: https://orcid.org/0000-0002-4609-6293)
- Michael Yankoski (ORCID: https://orcid.org/0000-0002-9654-6993)
- Tim Weninger (ORCID: https://orcid.org/0000-0003-3164-2615)
- Daniel Nguyen (ORCID: https://orcid.org/0000-0002-2486-4060)
- Mohammed Almutairi (ORCID: https://orcid.org/0009-0008-0819-9866)
- Svitlana Volkova (ORCID: https://orcid.org/0000-0002-6131-3073)
- Charles Chiang (ORCID: https://orcid.org/0009-0008-6079-4355)
- H.L. Guo
- Maria Milkowski (ORCID: https://orcid.org/0009-0007-5303-8036)
- Matthew Belcher
Institutions
- University of Notre Dame (US)
- William & Mary (US)
- Aptima (United States) (US)
Publication Details
- Published
- 2025-09-27
- DOI
- https://doi.org/10.1145/3746058.3758994
- Primary Topic
- Human-Automation Interaction and Safety
- Type
- article
- Field-Weighted Citation Impact
- 0.00