Geometry optimization of atomic structures is a common and crucial task in computational chemistry and materials design. Following the learning to optimize paradigm, we propose a new multi-agent reinforcement learning method called Multi-Agent Crystal Structure optimization (MACS) to address periodic crystal structure optimization. MACS treats geometry optimization as a partially observable Markov game in which atoms are agents that adjust their positions to collectively discover a stable configuration. We train MACS across various compositions of reported crystalline materials to obtain a policy that successfully optimizes structures from the training compositions as well as structures of larger sizes and unseen compositions, confirming its excellent scalability and zero-shot transferability. We benchmark our approach against a broad range of state-of-the-art optimization methods and demonstrate that MACS optimizes periodic crystal structures significantly faster, with fewer energy calculations, and the lowest failure rate.
@article{arxiv.2506.04195,
title = {MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures},
author = {Elena Zamaraeva and Christopher M. Collins and George R. Darling and Matthew S. Dyer and Bei Peng and Rahul Savani and Dmytro Antypov and Vladimir V. Gusev and Judith Clymo and Paul G. Spirakis and Matthew J. Rosseinsky},
journal= {arXiv preprint arXiv:2506.04195},
year = {2025}
}