PEMANT: Persona-Enriched Multi-Agent Negotiation for Travel

2026-04-12

AI Summary

This study addresses the limitations of existing household trip generation models, which lack grounding in behavioral theory and mechanisms to capture intra-household interactions, thereby failing to represent collective decision-making processes. To overcome this gap, the authors propose a novel Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework that integrates the Theory of Planned Behavior into large language models. The approach introduces a role-aligned control mechanism and constructs individualized role profiles to facilitate structured multi-agent dialogues that simulate household travel negotiations. Evaluated on both national and regional household travel datasets, the method significantly outperforms current benchmarks, achieving higher predictive accuracy while enhancing the behavioral plausibility and interpretability of the modeling process.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• trip generation
• household decision-making
• behavioral theory
• multi-agent negotiation
• travel modeling

Innovation

• LLM-based multi-agent negotiation
• behavioral theory integration
• persona modeling
• household travel decision
• structured conversation framework