PEMANT: Persona-Enriched Multi-Agent Negotiation for Travel

TL;DR

PEMANT is a novel LLM-based framework that models household travel decisions by integrating behavioral theory and multi-agent negotiation, improving prediction accuracy over existing methods.

Contribution

It introduces a theory-grounded persona modeling approach and a structured multi-agent negotiation framework for household trip planning.

Findings

PEMANT outperforms state-of-the-art benchmarks on national and regional datasets.

It encodes household attitudes and norms into narrative profiles for better decision modeling.

The framework effectively captures intra-household negotiation dynamics.

Abstract

Modeling household-level trip generation is fundamental to accurate demand forecasting, traffic flow estimation, and urban system planning. Existing studies were mostly based on classical machine learning models with limited predictive capability, while recent LLM-based approaches have yet to incorporate behavioral theory or intra-household interaction dynamics, both of which are critical for modeling realistic collective travel decisions. To address these limitations, we propose a novel LLM-based framework, named Persona-Enriched Multi-Agent Negotiation for Travel (PEMANT), which first integrates behavioral theory for individualized persona modeling and then conducts household-level trip planning negotiations via a structured multi-agent conversation. Specifically, PEMANT transforms static sociodemographic attributes into coherent narrative profiles that explicitly encode household-level attitudes, subjective norms, and perceived behavioral controls, following our proposed Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework. Building on these theory-grounded personas, PEMANT captures real-world household decision negotiation via a structured two-phase multi-agent conversation framework with a novel persona-alignment control mechanism. Evaluated on both national and regional household travel survey datasets, PEMANT consistently outperforms state-of-the-art benchmarks across datasets.