Generative Agents for High-Fidelity Simulation of Community-Scale Mobility and Energy Behavior

The transition to sustainable mobility and energy systems is a complex socio-technical challenge, where the success of new technologies and policies hinges on their interaction with human behavior. Traditional models often fail to capture the nuanced, heterogeneous, and adaptive nature of occupant decision-making, particularly in terms of mobility choices and energy use, creating a critical uncertainty gap for system design and policy evaluation. This paper presents a new paradigm to address this gap: a scalable, high-fidelity simulation framework based on Generative Agents. The framework's core innovations are twofold: 1) It leverages Large Language Models (LLMs) to autonomously generate agents with intrinsic personality traits autonomously, enabling a realistic simulation of diverse, human-like responses to environmental, social, and transportation-related cues. 2) It introduces a hierarchical "Prototype-Individual" architecture that makes large-scale simulation of entire communities computationally feasible. We validate this framework through a case study of a 495-agent community, demonstrating that our model reproduces aggregate mobility and energy consumption patterns—including key peak-load and temporal dynamics—with remarkable fidelity to real-world data. By providing a virtual testbed for human-in-the-loop analysis, this work offers a foundational tool for assessing the real-world viability of sustainable mobility designs, gauging the potential social and economic impacts of new transportation and energy policies, and mitigating the risks associated with investments in future sustainable infrastructure.