[2601.13508] Autonomous Computational Catalysis Research via Agentic Systems

Condensed Matter > Materials Science arXiv:2601.13508 (cond-mat) [Submitted on 20 Jan 2026 (v1), last revised 3 Apr 2026 (this version, v2)] Title:Autonomous Computational Catalysis Research via Agentic Systems Authors:Honghao Chen, Jiangjie Qiu, Yi Shen Tew, Xiaonan Wang View a PDF of the paper titled Autonomous Computational Catalysis Research via Agentic Systems, by Honghao Chen and 3 other authors View PDF HTML (experimental) Abstract:Fully automating the scientific process is a transformative ambition in materials science, yet current artificial intelligence masters isolated workflow fragments. 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 demanding evaluations, CatMaster achieves perfect scores on four end-to-end short-form catalysis scenarios, reaches near-leaderboard performance on five of six MatBench tasks, performs self-discovery of reaction mechanisms grounded in literature or from scratch, and executes a fully closed-loop single-atom catalyst design problem. Together, these results show that end-to-end autonomous computational catalysis is now...