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

TL;DR

This paper introduces a novel architecture combining Large Language Models with agent-based simulation to model realistic human mobility behavior in complex multimodal transport systems, demonstrated through a Toulouse case study.

Contribution

It presents an integrated framework using LLMs, GAMA, GTFS, and OpenTripPlanner for realistic, context-aware transport decision modeling in urban environments.

Findings

Agents make context-aware transport decisions

Agents develop habits over time in simulation

Framework effectively visualizes and evaluates mobility behavior

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.