Search papers, labs, and topics across Lattice.
This paper introduces an LLM-enhanced Agent-Based Model (ABM) for urban mobility simulation, addressing the limitations of rule-based ABMs in capturing realistic agent behavior. The framework uses an LLM to generate diverse synthetic population profiles, allocate locations, and simulate personalized routes based on real-world data from Taipei City. The resulting simulation provides route heatmaps and mode-specific indicators, offering actionable insights for urban planning.
LLMs can breathe life into urban mobility simulations, generating realistic agent behaviors and personalized routes that traditional rule-based models miss.
This study presents an innovative approach to urban mobility simulation by integrating a Large Language Model (LLM) with Agent-Based Modeling (ABM). Unlike traditional rule-based ABM, the proposed framework leverages LLM to enhance agent diversity and realism by generating synthetic population profiles, allocating routine and occasional locations, and simulating personalized routes. Using real-world data, the simulation models individual behaviors and large-scale mobility patterns in Taipei City. Key insights, such as route heat maps and mode-specific indicators, provide urban planners with actionable information for policy-making. Future work focuses on establishing robust validation frameworks to ensure accuracy and reliability in urban planning applications.
