An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction

Enhancing Travel Mode-Choice Modeling with Route-Based Attributes and Explainable Machine Learning

Modeling mode choice is essential for designing efficient and sustainable mobility systems. Revealed-preference surveys provide valuable information, but they rely on self-reported data, which can be biased and are typically unavailable for unchosen alternatives. This study proposes an integrated analytical process that combines revealed-preference survey data, route-level attributes derived from a digital trip planner, machine-learning classifiers, and explainable artificial intelligence (XAI) methods to evaluate predictive performance and behavioral interpretation jointly. Using a dataset of 1,372 trips collected in a university commuting context as an illustrative application, survey responses were enriched with mode-specific travel times and geometric characteristics of planner-recommended routes obtained from Google Maps’ application programming interface. Four tree-based classifiers were evaluated in a leak-free validation framework, and model behavior was interpreted using SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) at both the global and local levels. The results indicate that when route-level geometric attributes were combined with revealed-preference survey data, predictive accuracy remained comparable, whereas interpretability improved substantially. XAI analyses revealed that route characteristics such as straightness, sinuosity, and angular deviation emerged as significant predictors that modulated perceived travel effort, particularly for walking and public transport, despite their limited impact on aggregate performance.

Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data

Evaluating mobility interventions at tourist destinations requires predicting visitor behavior under varying conditions. Traditional methods struggle because tourist decisions depend heavily on context like weather and fatigue, yet models cannot generalize to unobserved scenarios. Large Language Models offer a solution by encoding commonsense knowledge about human behavior from pretraining, enabling reasoning about context-dependent decisions, while natural language representation flexibly integrates heterogeneous information. Fine-tuning on local trajectories adapts this general understanding to destination-specific patterns. We validate this approach using 566 trajectories from Wakayama Castle Park, Japan. Our fine-tuned Llama-3.1-8B achieves 49.1% next POI accuracy and maintains strong performance on undersampled scenarios like rainy days, demonstrating effective generalization. This establishes LLMs as high-fidelity behavior models for context-dependent tourist prediction, providing groundwork for counterfactual analysis of mobility interventions.

An AI-Powered Location-Based Recommendation System for Personalized Urban Mobility

TravelBehaviorQA: A Benchmark Dataset for Behavioral Interpretation of GPS Trajectories

GPS trajectories encode rich behavioral information about how people move, organize activities, and form daily routines. Recent advances in large language models (LLMs) raise a natural question: can such models infer and summarize travel behavior directly from mobility traces? This paper introduces Travel-BehaviorQA , a large-scale benchmark dataset that reframes trajectory analysis as a language-based behavioral understanding task. The dataset links raw GPS trajectories with human-grounded question-answering (QA) pairs that capture travel intensity, temporal structure, activity patterns, mode usage, and behavioral routines. Unlike prior mobility datasets focused on prediction or classification, TravelBehaviorQA emphasizes semantic interpretation through a unified mix of deterministic and open-ended questions. In this benchmark, we construct over 143k QA instances spanning users and years, and evaluate a broad range of state-of-the-art LLMs under controlled settings. Our results reveal substantial gaps between factual extraction and genuine behavioral reasoning, showing that model scale alone is insufficient and that trajectory representation is a primary bottleneck. TravelBehaviorQA exposes critical limitations of current models and establishes a rigorous benchmark for advancing language-based understanding of human mobility behavior. The dataset is available at https://github.com/

AgentCity: An AI-Maintained Continuous Benchmark for Traffic Prediction

Traffic prediction is a fundamental component of intelligent transportation systems, and recent research has explored a wide range of prediction tasks and modeling approaches. While several benchmarking frameworks have been proposed to support fair and reproducible evaluation, most existing benchmarks rely on manual maintenance, making it difficult to continuously integrate new models and evaluate them under a unified set of data processing and evaluation protocols as the literature grows. In this work, we present AgentCity, an AI-maintained framework for the continuous construction and evaluation of traffic prediction benchmarks. AgentCity formulates benchmark maintenance as an automated, agent-driven workflow that supports literature retrieval, model and data integration, and standardized evaluation under unified protocols. Built on top of AgentCity, we release a publicly accessible traffic prediction benchmark1 covering four representative tasks, including traffic state prediction, trajectory location prediction, estimated time of arrival prediction, and map matching, and aggregate 74 representative models evaluated across multiple datasets under consistent evaluation settings, together with task-wise leaderboards and detailed evaluation records. We further validate the reliability of AgentCity through benchmark validation studies on reproduction fidelity and consistency across different code-oriented agents. By automating key stages of benchmark maintenance, AgentCity supports the continuous integration and evaluation of traffic prediction models under unified protocols. 1Project website: https://www.agentcity.city/ Source code: https://github.com/Beihang-BIGSCity/AgentCity.

Large Behavior Model: A Promptable Digital Twin of the Retail Customer

Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person-Environment formulation. Customer state is represented by a behavioral profile derived from historical purchases, while product context is incorporated through retrieval-augmented generation. The model is trained using continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration. We evaluate the proposed framework on purchase prediction, hard-negative discrimination, basket completion, promotion response, and cross-domain voucher redemption. The model consistently outperforms frontier general-purpose language models on in-domain retail tasks while demonstrating strong zero-shot and fine-tuned transfer across retailers and decision domains. Ablation studies show that continued pre-training is the primary driver of behavioral generalization, retrieval is most effective when applied during both training and inference, and reinforcement learning improves reliance on explicit behavioral evidence over generic language-model priors. These results demonstrate that behavioral knowledge encoded in transaction histories can be effectively learned by language models, providing a scalable foundation for customer digital twins and behavior simulation.