Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Do, Hunmin, Yoon, Taejun, Jung, Kiyong
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.21696
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915883055579136
author Do, Hunmin
Yoon, Taejun
Jung, Kiyong
author_facet Do, Hunmin
Yoon, Taejun
Jung, Kiyong
contents While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21696
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MIND: Multi-agent inference for negotiation dialogue in travel planning
Do, Hunmin
Yoon, Taejun
Jung, Kiyong
Artificial Intelligence
While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.
title MIND: Multi-agent inference for negotiation dialogue in travel planning
topic Artificial Intelligence
url https://arxiv.org/abs/2603.21696