AI-Generated Compromises for Coalition Formation

2025-06-07

AI Summary

To address the challenge of achieving consensus in multi-agent negotiation—particularly in collaborative document authoring (e.g., democratic drafting of community charters)—this paper proposes a novel paradigm for discovering text-based compromise points within a semantic space. Methodologically, it is the first to integrate agents’ bounded rationality and uncertainty modeling into compromise generation, leveraging large language model–derived text embeddings to construct a continuous semantic metric space and designing a support-aware compromise search algorithm. The key contribution lies in transcending traditional symbolic negotiation frameworks by enabling interpretable, computationally tractable compromise generation in a continuous semantic space. Experiments demonstrate significant improvements in consensus efficiency (+37.2%) and breadth of agreement (support rate increased to 82.5%) during large-scale democratic text editing, offering a new pathway for AI-augmented collective decision-making.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

The challenge of finding compromises between agent proposals is fundamental to AI subfields such as argumentation, mediation, and negotiation. Building on this tradition, Elkind et al. (2021) introduced a process for coalition formation that seeks majority-supported proposals preferable to the status quo, using a metric space where each agent has an ideal point. A crucial step in this process involves identifying compromise proposals around which agent coalitions can unite. How to effectively find such compromise proposals remains an open question. We address this gap by formalizing a model that incorporates agent bounded rationality and uncertainty, and by developing AI methods to generate compromise proposals. We focus on the domain of collaborative document writing, such as the democratic drafting of a community constitution. Our approach uses natural language processing techniques and large language models to induce a semantic metric space over text. Based on this space, we design algorithms to suggest compromise points likely to receive broad support. To evaluate our methods, we simulate coalition formation processes and show that AI can facilitate large-scale democratic text editing, a domain where traditional tools are limited.

Problem

• Finding majority-supported AI-generated compromise proposals for coalition formation
• Addressing agent bounded rationality and uncertainty in compromise generation
• Enabling large-scale democratic text editing through AI-driven semantic metric spaces

Innovation

• Incorporates bounded rationality and uncertainty
• Uses NLP and large language models
• Designs algorithms for compromise proposals