MIND: Multi-agent inference for negotiation dialogue in travel planning
This work addresses the challenge of realistic consensus-building among travelers with heterogeneous preferences, representing an incremental advance in multi-agent debate research.
The paper tackles the problem of coordinating complex stakeholder interests in travel planning by proposing MIND, a multi-agent framework for negotiation dialogue, which achieves a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate over traditional methods.
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.