Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

TL;DR

This paper introduces a novel method that combines large language models with Bayesian frameworks to improve opponent preference estimation in multi-agent negotiations by leveraging natural language cues.

Contribution

It presents a new approach that integrates natural language understanding into structured Bayesian opponent modeling, enhancing preference estimation accuracy.

Findings

Improved full agreement rate in multi-party negotiations.

Enhanced preference estimation accuracy through natural language cues.

Effective integration of LLMs with probabilistic reasoning.

Abstract

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.