Visualizing Coalition Formation: From Hedonic Games to Image Segmentation
Abstract
We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study how a granularization parameter shapes equilibrium fragmentation and boundary structure. On the Weizmann single-object benchmark, we relate multi-coalition equilibria to binary protocols by measuring whether the converged coalitions overlap with a foreground ground-truth. We observe transitions from cohesive to fragmented yet recoverable equilibria, and finally to intrinsic failure under excessive fragmentation. Our core contribution links multi-agent systems with image segmentation by quantifying the impact of mechanism design parameters on equilibrium structures.
Cite
@article{arxiv.2603.07890,
title = {Visualizing Coalition Formation: From Hedonic Games to Image Segmentation},
author = {Pedro Henrique de Paula França and Lucas Lopes Felipe and Daniel Sadoc Menasché},
journal= {arXiv preprint arXiv:2603.07890},
year = {2026}
}
Comments
The First Workshop on AI for Mechanism Design and Strategic Decision Making -- Workshop AIMS at ICLR 2026