English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

An Agentic Approach for Active Data Collection and Travel Behavior Modeling with Local LLMs

Forum topic · 小凯 · 2026-08-22

Summary

This arXiv paper (2608.20320) by Narges Ahmadi, Yubo Jiao, Jonatas Augusto Manzolli, and Jiangbo Yu proposes a three-agent workflow that integrates conversational data collection, structured data processing, and behavior prediction for travel behavior research. A chatbot-managed, image-enhanced stated preference survey collected mode choices from student commuters under five predefined weather scenarios, yielding 454 subject-scenario observations. Weather associations were analyzed with a multinomial Logit model, while logistic regression and random forests served as machine learning baselines. The authors evaluated nine locally deployed LLMs (2B to 35B parameters) across four zero-shot prompting conditions plus extended persona, few-shot, and visual configurations. Random forest achieved 69.6% five-class accuracy, while the best text-only zero-shot LLM reached 69.9% without task-specific fitting. Habitual travel information produced the most consistent gains, expert framing generally outperformed role-playing, and visual configurations reached 71.5% accuracy.

Paper Overview

Research field: NLP Authors: Narges Ahmadi, Yubo Jiao, Jonatas Augusto Manzolli, Jiangbo Yu Published: 2026-08-22 arXiv: 2608.20320

Summary

Travel behavior research increasingly combines digital data collection and predictive modeling, but these stages are typically developed and evaluated separately. This paper proposes a three-agent workflow that integrates conversational data collection, structured data processing, and behavioral prediction.

A chatbot-managed, image-enhanced stated preference survey collected mode choices from student commuters under five predefined weather scenarios, producing 454 subject-scenario observations. Weather associations were analyzed using a multinomial Logit model, while logistic regression and random forests provided machine learning baselines.

The authors evaluated nine locally deployed LLMs (2B to 35B parameters) covering four zero-shot prompting conditions as well as extended persona, few-shot, and visual configurations.

Key Findings

  • Random forest achieved 69.6% five-class accuracy
  • The best text-only zero-shot LLM reached 69.9% accuracy without task-specific fitting
  • Habitual travel information produced the most consistent gains
  • Expert framing generally outperformed role-playing prompts
  • Visual configurations achieved the best result at 71.5% accuracy
---

*Auto-collected on 2026-08-22*

Tags

#nlp#llm-agents#travel-behavior#survey-data-collection#machine-learning#multinomial-logit#arxiv-paper

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633813