MiCRO for Multilateral Negotiations

2025-10-20

AI Summary

Existing multi-party negotiation approaches rely heavily on opponent modeling, parameter tuning, and complex learning mechanisms, limiting their interpretability, robustness, and deployment efficiency. To address this, we extend MiCRO—the first model-free, parameter-free bilateral negotiation strategy—to the multi-party setting, proposing the first generalizable MiCRO framework for multi-lateral negotiation. Our method employs rule-based decision-making coupled with empirical game-theoretic analysis, eschewing machine learning and explicit opponent modeling; it provably converges to an empirical Nash equilibrium. Evaluated against champion strategies from ANAC 2015–2018, our approach achieves significantly higher negotiation efficiency and robustness than state-of-the-art methods. This demonstrates the effectiveness and broad applicability of lightweight, interpretable, and tuning-free paradigms in complex multi-party negotiation domains.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Game Theory and Economic Paradigms: Mechanism Design
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recently, a very simple new bilateral negotiation strategy called MiCRO was introduced that does not make use of any kind of opponent modeling or machine learning techniques and that does not require fine-tuning of any parameters. Despite its simplicity, it was shown that MiCRO performs similar to -- or even better than -- most state-of-the-art negotiation strategies. This lead its authors to argue that the benchmark domains on which negotiation algorithms are typically tested may be too simplistic. However, one question that was left open, was how MiCRO could be generalized to multilateral negotiations. In this paper we fill this gap by introducing a multilateral variant of MiCRO. We compare it with the winners of the Automated Negotiating Agents Competitions (ANAC) of 2015, 2017 and 2018 and show that it outperforms them. Furthermore, we perform an empirical game-theoretical analysis to show that our new version of MiCRO forms an empirical Nash equilibrium.

Problem

• Extending MiCRO strategy to multilateral negotiation settings
• Comparing performance with ANAC competition-winning negotiation agents
• Proving empirical Nash equilibrium in multilateral negotiation scenarios

Innovation

• Multilateral variant of MiCRO without opponent modeling
• Outperforms ANAC competition winners empirically
• Forms empirical Nash equilibrium in analysis