Modeling realistic human behaviour to understand people's mode choices in order to propose personalised mobility solutions remains challenging. This paper presents an architecture for modeling realistic human mobility behavior in complex multimodal transport systems, demonstrated through a case study in Toulouse, France. We apply Large Language Models (LLMs) within an agent-based simulation to capture decision-making in a real urban setting. The framework integrates the GAMA simulation platform with an LLM-based generative agent, along with General Transit Feed Specification (GTFS) data for public transport, and OpenTripPlanner for multimodal routing. GAMA platform models the interactive transport environment, providing visualization and dynamic agent interactions while eliminating the need to construct the simulation environment from scratch. This design enables a stronger focus on developing generative agents and evaluating their performance in transport decision-making processes. Over a simulated month, results show that agents not only make context-aware transport decisions but also form habits over time. We conclude that combining LLMs with agent-based simulation offers a promising direction for advancing intelligent transportation systems and personalised multimodal mobility solutions. We also discuss some limitations of this approach and outline future work on scaling to larger regions, integrating real-time data, and refining memory models.

翻译：为理解人们的出行方式选择并提出个性化出行方案，对真实人类行为进行建模仍然具有挑战性。本文提出了一种在复杂多模态交通系统中建模真实人类出行行为的架构，并通过法国图卢兹的案例研究进行验证。我们在基于代理的仿真中应用大语言模型，以捕捉真实城市环境中的决策过程。该框架将GAMA仿真平台与基于LLM的生成代理相结合，并集成了用于公共交通的通用交通数据规范数据以及用于多模态路径规划的OpenTripPlanner。GAMA平台对交互式交通环境进行建模，提供可视化与动态代理交互功能，同时避免了从零构建仿真环境的需要。这种设计使得研究重点能更集中于开发生成代理并评估其在交通决策过程中的性能。在一个月的仿真周期内，结果表明代理不仅能做出情境感知的交通决策，还会随时间形成出行习惯。我们得出结论：将LLM与基于代理的仿真相结合，为推进智能交通系统与个性化多模态出行解决方案提供了有前景的研究方向。本文还讨论了该方法的若干局限性，并展望了未来在扩大模拟区域规模、整合实时数据以及优化记忆模型等方面的工作。