New agentic workflow integrates LLMs for travel behavior prediction

Researchers have developed a novel three-agent workflow that integrates conversational data collection, structured data processing, and behavioral prediction for travel behavior research. This approach utilizes a chatbot-administered survey to gather mode choices under various weather conditions, yielding data analyzed by traditional models and machine learning techniques. The study evaluated nine large language models (LLMs) with different prompting strategies, finding that multimodal LLMs incorporating visual context achieved the highest prediction accuracy. AI

IMPACT Demonstrates how LLMs can be integrated into complex data collection and prediction workflows, potentially improving accuracy in specialized domains.

RANK_REASON Research paper published on arXiv detailing a new methodology. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Hugging Face
• large-language models
• logistic regression model
• Multinomial Logit Model of Pedestrian Crossing Behaviors at Signalized Intersections
• random forest
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →