GTA: Generative Traffic Agents for Simulating Realistic Mobility Behavior
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation cites Generative Agents: Interactive Simulacra of Human Behavior
- Generative Agents: Interactive Simulacra of Human Behavior cites Evaluating Large Language Models in Generating Synthetic HCI Research Data: a Case Study
- Generative Agents: Interactive Simulacra of Human Behavior cites Social Simulacra: Creating Populated Prototypes for Social Computing Systems
Builds on6
- Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
- Evaluating Large Language Models in Generating Synthetic HCI Research Data: a Case StudyPerttu Hämäläinen, Mikke Tavast, Anton KunnariCHI 2023 · 244 citations
- Social Simulacra: Creating Populated Prototypes for Social Computing SystemsJoon Sung Park, Lindsay Popowski, Carrie J. Cai, Meredith Ringel Morris et al.UIST 2022 · 192 citations
- Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility GenerationJiawei Wang, Renhe Jiang, Chuang Yang, Zengqing Wu et al.NeurIPS 2024 · 181 citations
- Changes in Research Ethics, Openness, and Transparency in Empirical Studies between CHI 2017 and CHI 2022Kavous Salehzadeh Niksirat, Lahari Goswami, Pooja Rao S. B., James Tyler et al.CHI 2023 · 43 citations
Related papers
- Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in PersonasSalvatore Giorgi, Tingting Liu, Ankit Aich, Kelsey Isman et al.EMNLP Findings 2024 · 4 citations
- Mind the Gap: The Divergence Between Human and LLM-Generated TasksYi-Long Lu, Jiajun Song, Chunhui Zhang, Wei WangAAAI 2026
- Interview-Informed Generative Agents for Product Discovery: A Validation StudyZichao Wang, Alexa F. SiuCHI 2026 · 1 citation
- Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User StudiesZiyi Xuan, Yiwen Wu, Xuhai Xu, Vinod Namboodiri et al.UbiComp 2026 · 2 citations
- Graph-Based Alternatives to LLMs for Human SimulationJoseph Suh, Suhong Moon, Serina ChangACL 2026 · 2 citations
