CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation
This provides a scalable, flexible testbed for social science, behavioral studies, and urban planning, though it is incremental as it builds on existing LLM capabilities for simulation.
The paper tackled the problem of modeling human behavior in urban environments by developing CitySim, a large-scale LLM-driven agent simulation, which showed closer alignment with real humans than prior work at micro and macro levels and enabled experiments with tens of thousands of agents for tasks like crowd density estimation and place popularity prediction.
Modeling human behavior in urban environments is fundamental for social science, behavioral studies, and urban planning. Prior work often rely on rigid, hand-crafted rules, limiting their ability to simulate nuanced intentions, plans, and adaptive behaviors. Addressing these challenges, we envision an urban simulator (CitySim), capitalizing on breakthroughs in human-level intelligence exhibited by large language models. In CitySim, agents generate realistic daily schedules using a recursive value-driven approach that balances mandatory activities, personal habits, and situational factors. To enable long-term, lifelike simulations, we endow agents with beliefs, long-term goals, and spatial memory for navigation. CitySim exhibits closer alignment with real humans than prior work, both at micro and macro levels. Additionally, we conduct insightful experiments by modeling tens of thousands of agents and evaluating their collective behaviors under various real-world scenarios, including estimating crowd density, predicting place popularity, and assessing well-being. Our results highlight CitySim as a scalable, flexible testbed for understanding and forecasting urban phenomena.