Preference Estimation via Opponent Modeling in Multi-Agent Negotiation
For researchers in automated negotiation, this work provides a method to incorporate qualitative language information into quantitative opponent models, addressing a known limitation of numerical-only approaches.
The paper addresses the challenge of opponent modeling in multi-agent negotiation by integrating natural language cues from LLMs into a Bayesian framework, achieving improved full agreement rate and preference estimation accuracy on a multi-party benchmark.
Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. Although Large Language Models (LLMs) enable rich semantic understanding of utterances, it remains challenging to quantitatively incorporate such information into a consistent opponent modeling. To tackle this issue, we propose a novel preference estimation method integrating natural language information into a structured Bayesian opponent modeling framework. Our approach leverages LLMs to extract qualitative cues from utterances and converts them into probabilistic formats for dynamic belief tracking. Experimental results on a multi-party benchmark demonstrate that our framework improves the full agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding.