Fully autonomous science has long been a defining ambition for artificial intelligence in materials discovery, yet its realization requires more than automating isolated calculations. In computational catalysis, a system autonomously navigating the entire research lifecycle from conception to a scientifically meaningful manuscript remains an open challenge. Here we present CatMaster, a catalysis-native multi-agent framework that couples project-level reasoning with the direct execution of atomistic simulations, machine-learning modelling, literature analysis, and manuscript production within a unified autonomous architecture. Across progressively more realistic research settings, CatMaster converts natural-language intent into executable computational tasks, achieves near-ceiling scores on standard catalysis scenarios, reaches near-leaderboard performance on five of six MatBench tasks, performs autonomous modelling on various catalytic surfaces and reaction pathway investigations, and demonstrates the close-loop autonomy by a fully closed-loop single-atom catalyst design case. These results establish autonomous computational catalysis as an already operational scientific paradigm, while highlighting that bridging the gap to complex physical challenges and genuine scientific closure requires tighter integration with human stewardship and domain-rigorous methodologies in the future.
@article{arxiv.2601.13508,
title = {Toward Autonomous Computational Catalysis Research via Agentic Systems},
author = {Honghao Chen and Jiangjie Qiu and Yi Shen Tew and Xiaonan Wang},
journal= {arXiv preprint arXiv:2601.13508},
year = {2026}
}