Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

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

Source

arXiv

arxiv.org/abs/2608.20320v1

Read the source

Source

  • Source name: arXiv
  • Source kind: paper
  • Authors / organization: Narges Ahmadi, Yubo Jiao, Jônatas Augusto Manzolli, Jiangbo Yu, Luis Miranda-Moreno
  • Venue: arXiv: cs.AI
  • Published: 2026-08-20
  • Collected: 2026-08-21
  • URL: http://arxiv.org/abs/2608.20320v1
  • PDF: https://arxiv.org/pdf/2608.20320v1
  • DOI: UNKNOWN
  • Registry group: academic_apis_and_preprints
  • Evidence role: canonical_academic_index
  • Language: en
  • Country / region: UNKNOWN

Plain-Language Brief

This research proposes a three-step workflow integrating chatbot-administered surveys, data processing, and behavioral prediction for travel behavior modeling and weather-sensitive demand forecasting. The study uses 454 observations from student commuters across five weather scenarios. Machine learning models and large language models were tested, with the best achieving 71.5% accuracy using visual context.

What the Document Says

  • The research combines digital data collection and predictive modeling for travel behavior.
  • A three-agent workflow is proposed: chatbot-administered surveys, structured data processing, and behavioral prediction.
  • A survey was conducted with 454 student commuter respondents across five weather scenarios.
  • The study analyzes weather-related associations using a multinomial logit model and provides machine learning benchmarks.
  • Nine large language models were evaluated for their performance in four zero-shot conditions and extended through various configurations.
  • Random forest achieved 69.6% accuracy, while the best text-only LLM reached 69.9% without task-specific fitting.
  • Habitual travel information provided the most consistent gains, Expert framing outperformed Role-Play, and persona information was useful when habitual was unavailable.
  • Few-shot prompting improved prediction for several models, with gains stabilizing after a small number of examples.
  • Using the same weather images as respondents, the best vision-based configuration reached 71.5% accuracy.
  • The study shows how these different components can be coordinated within an auditable multi-agent workflow.

Key Concepts Mentioned

  • digital data collection
  • travel behavior modeling
  • weather-sensitive demand prediction
  • chatbot
  • stated-preference survey
  • multinomial logit model
  • large language models
  • machine learning
  • conversational surveys

Claims Made by the Document

  • The proposed three-agent workflow integrates conversational data collection, structured data processing, and behavioral prediction.
  • Random forest achieved 69.6% five-class accuracy.
  • The best text-only LLM reached 69.9% accuracy without task-specific fitting.
  • Habitual travel information provided the most consistent gains.
  • Expert framing generally outperformed Role-Play.
  • Persona information was most useful when habitual travel information was unavailable.
  • Few-shot prompting improved prediction for several models.
  • Using visual context may provide additional predictive information for selected models.
  • The study demonstrates the coordination of conversational surveys, machine learning, and large language models within an auditable multi-agent workflow.

Evidence Used

  • 454 respondent-scenario observations from a chatbot-administered survey
  • results from multinomial logit model analysis
  • performance metrics of nine large language models

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Travel behavior research increasingly combines digital data collection with predictive modeling, yet these stages are often developed and evaluated separately. This study proposes a three-agent workflow integrating conversational data collection, structured data processing, and behavioral prediction. A chatbot-administered, image-augmented stated-preference survey collected mode choices from student commuters across five predefined weather scenarios, yielding 454 respondent-scenario observations. Weather-related associations were analyzed using a multinomial logit model, while logistic regression and random forest provided machine-learning benchmarks. Nine locally deployed large language models (LLMs), ranging from 2 to 35 billion parameters, were evaluated across four zero-shot prompt-and-context conditions and extended through persona, few-shot, and vision-based 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-Play, and persona information was most useful when habitual travel information was unavailable. Few-shot prompting improved prediction for several models, with gains stabilizing after a small number of examples. Using the same weather images shown to respondents, the best vision-based configuration reached 71.5% five-class accuracy, indicating that visual context may provide additional predictive information for selected models. Overall, the study shows how conversational surveys, structured data processing, conventional behavioral modeling, machine learning, and multimodal LLM prediction can be coordinated within an auditable multi-agent workflow.