Modeling realistic human behavior using generative agents in a multimodal transport system: Software architecture and Application to Toulouse

TL;DR

The paper tackles the challenge of modeling realistic multimodal mobility by integrating generative agents with a spatially explicit simulation (GAMA) and real-world transit data (GTFS/OSM). It proposes an architecture where LLM-driven agents plan, perceive, and reflect within a multimodal transport network, leveraging OpenTripPlanner for routing and a dual memory system to form habits over time. Key contributions include a detailed software architecture, an implementation on Toulouse's transport network, and empirical evidence of context-aware decisions and habit formation, as well as a comparison across several LLMs and memory configurations. The study advances intelligent transportation research by offering a scalable, data-driven framework for personalized mobility and highlights practical considerations for cost, validation, and future extensions to real-time data, larger populations, and hybrid models.

Abstract

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.

Figures (14)

• Figure 1: The public transport system of Toulouse, France, combining metro, tram, bus, and cable car, visualized in the GAMA platform with GTFS data.
• Figure 2: The architecture of the proposed framework, integrating the GAMA platform with Generative Agents and the OpenTripPlanner module.
• Figure 3: An example of multimodal routing using OpenTripPlanner. The map shows the public transport network in Toulouse, France.
• Figure 4: The memory stream consists of historical experiences that may be relevant to the current transport context. A retrieval step identifies a subset of these experiences to be provided to the language model, enabling more informed selection among the available travel options.
• Figure 5: Data exchange pipeline between GAMA and LLM GAs.