AI-Generated Compromises for Coalition Formation: Modeling, Simulation, and a Textual Case Study

2025-11-27

AI Summary

Generating computationally tractable and interpretable compromise solutions in multi-agent collaborative text authoring—such as community constitution drafting—remains challenging due to semantic heterogeneity and preference uncertainty. Method: This paper proposes the first compromise generation framework integrating semantic embedding with coalition formation theory. It maps LLM-derived textual semantics into a metric space, formally defines a “compromise point” based on semantic density and preference coverage, and models bounded rationality and uncertainty via LLM fine-tuning and prompt engineering. Contribution/Results: Evaluated on constitution-drafting simulations, the method increases cross-stance coalition formation rates by 3.2× compared to baselines, enables efficient consensus convergence among heterogeneous groups of up to 100 agents, and significantly outperforms conventional voting mechanisms and collaborative editing tools in both scalability and interpretability.

Technology Category

• Multiagent Systems: Mechanism Design
• Knowledge Representation and Reasoning: Preferences
• Natural Language Processing: Safety and Robustness

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: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The challenge of finding compromises between agent proposals is fundamental to AI sub-fields 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. The crucial step in this iterative process involves identifying compromise proposals around which agent coalitions can unite. How to effectively find such compromise proposals, however, remains an open question. We address this gap by formalizing a holistic model that encompasses agent bounded rationality and uncertainty and developing AI models to generate such compromise proposals. We focus on the domain of collaboratively writing text documents -- e.g., to enable the democratic creation of a community constitution. We apply NLP (Natural Language Processing) techniques and utilize LLMs (Large Language Models) to create a semantic metric space for text and develop algorithms to suggest suitable compromise points. To evaluate the effectiveness of our algorithms, we simulate various coalition formation processes and demonstrate the potential of AI to facilitate large-scale democratic text editing, such as collaboratively drafting a constitution, an area where traditional tools are limited.

Problem

• Finding compromise proposals for coalition formation
• Applying AI and NLP to collaborative text document writing
• Simulating coalition processes to evaluate AI effectiveness

Innovation

• Using NLP and LLMs to create semantic metric spaces
• Developing algorithms to suggest compromise proposals for coalitions
• Simulating coalition processes to evaluate AI's democratic text editing