Enabling User-Created Multi-Agent Simulations: Interactive and Customizable 2D Environments to Study Team Dynamics with LLM Agents
Abstract
Enabling users to create their own simulations offers a powerful way to study how environments shape agent behavior and intelligence. We introduce VirtLab, a system that allows researchers and practitioners to design interactive, customizable simulations of team dynamics with LLM-based agents situated in 2D spatial environments. Unlike prior frameworks that restrict scenarios to predefined or static tasks, our approach empowers users to build environments, assign roles, and observe how agents coordinate, move, and adapt over time. A web-based interface makes these simulations accessible to both technical and non-technical users, supporting the design, execution, and analysis of complex multi-agent experiments without programming. By bridging team cognition behaviors with scalable agent-based modeling, our system provides a testbed for investigating how diverse environments influence coordination, collaboration, and emergent team behaviors. We demonstrate its utility by aligning simulated outcomes with empirical evaluations and a user study, underscoring the importance of customizable environments for advancing research on collective intelligence and adaptive agents.