Learning Multi-Agent Coordination via Sheaf-ADMM

Excited to share our paper, “Learning Multi-Agent Coordination via Sheaf-ADMM” to be presented at ICML 2026. Technical Blog: pub.sakana.ai/sheaf-admm Full paper: arxiv.org/abs/2605.31005 Code: github.com/SakanaAI/sheaf Most AI models process information as one giant, monolithic block. But in nature, intelligence often comes from a group of individuals working together, where each individual only has a limited view of the world. We built a framework called Sheaf-ADMM to study how thi