GTA: Generative Traffic Agents for Simulating Realistic Mobility Behavior

2026-01-23

AI Summary

This study addresses the limitations of traditional traffic behavior modeling, which relies on handcrafted rules and expensive data, making it ill-suited for predicting large-scale human mobility responses during the early stages of emerging technologies or policies. The authors propose a large language model (LLM)-driven framework that generates synthetic populations from census data and simulates context-sensitive activity schedules and mode choices without manual rule specification. This work represents the first application of LLM-based personalized agents to city-scale transportation simulation, enabling flexible evaluation of novel interventions such as bike lanes or mobility apps. Experiments in Berlin demonstrate the model’s ability to reproduce observed travel mode distributions across socioeconomic groups, despite systematic biases in trip distance and mode preference, thereby validating its potential and scalability for urban mobility analysis.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

People's transportation choices reflect complex trade-offs shaped by personal preferences, social norms, and technology acceptance. Predicting such behavior at scale is a critical challenge with major implications for urban planning and sustainable transport. Traditional methods use handcrafted assumptions and costly data collection, making them impractical for early-stage evaluations of new technologies or policies. We introduce Generative Traffic Agents (GTA) for simulating large-scale, context-sensitive transportation choices using LLM-powered, persona-based agents. GTA generates artificial populations from census-based sociodemographic data. It simulates activity schedules and mode choices, enabling scalable, human-like simulations without handcrafted rules. We evaluate GTA in Berlin-scale experiments, comparing simulation results against empirical data. While agents replicate patterns, such as modal split by socioeconomic status, they show systematic biases in trip length and mode preference. GTA offers new opportunities for modeling how future innovations, from bike lanes to transit apps, shape mobility decisions.

Problem

• mobility behavior
• transportation choice
• urban planning
• sustainable transport
• behavioral simulation

Innovation

• Generative Traffic Agents
• LLM-powered agents
• persona-based simulation
• large-scale mobility modeling
• context-sensitive transportation choice