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

arXiv: https://arxiv.org/abs/2608.20320 · HTML: https://mlsanity.com/paper/2608.20320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [Character is Destiny: Can Role-Playing Language Agents Make Persona-Driven Decisions?](https://mlsanity.com/paper/2404.12138/) (2024)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [Large Language Models for Travel Behavior Prediction](https://mlsanity.com/paper/2312.00819/) (2023)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [Submitting surveys via a conversational interface: an evaluation of user acceptance and approach effectiveness](https://mlsanity.com/paper/2003.02537/) (2020)
- [Synthesizing Attitudes, Predicting Actions (SAPA): Behavioral Theory-Guided LLMs for Ridesourcing Mode Choice Modeling](https://mlsanity.com/paper/2509.18181/) (2025)
- [LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior](https://mlsanity.com/paper/2510.18155/) (2025)
- [Aligning LLM agents with human learning and adjustment behavior: a dual agent approach](https://mlsanity.com/paper/2511.00993/) (2025)
- [AURA: A Reinforcement Learning Framework for AI-Driven Adaptive Conversational Surveys](https://mlsanity.com/paper/2510.27126/) (2025)
- [MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment](https://mlsanity.com/paper/2603.17694/) (2026)
- [Talking Surveys: How Photorealistic Embodied Conversational Agents Shape Response Quality, Engagement, and Satisfaction](https://mlsanity.com/paper/2508.02376/) (2025)
- [Using Large Language Models to Construct Virtual Top Managers: A Method for Organizational Research](https://mlsanity.com/paper/2601.18512/) (2026)
- [Assessing the Feasibility of a Video-Based Conversational Chatbot Survey for Measuring Perceived Cycling Safety: A Pilot Study in New York City](https://mlsanity.com/paper/2604.07375/) (2026)

## Abstract (arXiv)

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.