Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework
Tianming Liu, Jirong Yang, Yafeng Yin
TL;DR
The paper addresses the challenge of accurately modeling transportation demand amidst complex traveler behavior by proposing an LLM-agent-based framework that integrates autonomous, memory-enabled travelers with a dynamic network simulator. By combining LLM reasoning, perception, and memory with activity-based travel planning, the approach aims to relax restrictive behavioral assumptions, improve data efficiency, and enable flexible policy evaluation. A proof-of-concept demonstrates that LLM agents can autonomously generate context-aware activities, format travel plans for simulators, and learn from system feedback to adjust behavior toward equilibrium. The work highlights both the potential benefits for transportation planning and the substantial challenges of behavioral fidelity, scalability, and rigorous validation, recommending a hybrid modeling path as a practical near-term strategy.
Abstract
In transportation system demand modeling and simulation, agent-based models and microsimulations are current state-of-the-art approaches. However, existing agent-based models still have some limitations on behavioral realism and resource demand that limit their applicability. In this study, leveraging the emerging technology of large language models (LLMs) and LLM-based agents, we propose a general LLM-agent-based modeling framework for transportation systems. We argue that LLM agents not only possess the essential capabilities to function as agents but also offer promising solutions to overcome some limitations of existing agent-based models. Our conceptual framework design closely replicates the decision-making and interaction processes and traits of human travelers within transportation networks, and we demonstrate that the proposed systems can meet critical behavioral criteria for decision-making and learning behaviors using related studies and a demonstrative example of LLM agents' learning and adjustment in the bottleneck setting. Although further refinement of the LLM-agent-based modeling framework is necessary, we believe that this approach has the potential to improve transportation system modeling and simulation.