Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

2026-04-17

AI Summary

This work addresses the challenge of unstable preference estimation in multi-agent negotiation, where traditional numerical methods struggle to accurately and comprehensively infer opponents’ preferences from natural language interactions. To overcome this limitation, the paper proposes a novel opponent modeling framework that integrates large language models (LLMs) with Bayesian inference. The approach leverages the semantic understanding capabilities of LLMs to extract qualitative preference cues from dialogue and translates them into probabilistic beliefs that are dynamically updated over time. This is the first method to combine LLM-based linguistic interpretation with structured Bayesian modeling for quantitative and dynamic representation of latent preferences. Experimental results demonstrate that the proposed framework significantly improves both the rate of full agreement and the accuracy of preference estimation on established multi-party negotiation benchmarks.

Technology Category

• Knowledge Representation and Reasoning: Preferences
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Machine Learning: Learning Preferences or Rankings

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: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

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.

Problem

• Preference Estimation
• Opponent Modeling
• Multi-Agent Negotiation
• Natural Language Understanding
• Large Language Models

Innovation

• opponent modeling
• preference estimation
• large language models
• Bayesian framework
• multi-agent negotiation