Arche system autonomously discovers chemical reaction mechanisms
Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
Artificial Intelligence
Summary
Figuring out how chemicals react with each other is important in chemistry but usually needs experts to guide computer simulations. The authors created ARCHE, a system that thinks like a scientist by forming and testing ideas about chemical reactions on its own. It uses computer models and tools to check these ideas carefully and improve them step by step. They tested ARCHE on different chemical problems and showed it can choose and confirm explanations without human help. This work could help speed up the discovery of new chemical reactions and improve automated research.
What this means in practice
- •For chemical engineers: Automate proposing and validating reaction pathways to accelerate process design in catalysis and organic synthesis.
- •For computational chemists: Integrate ARCHE to reduce manual intervention when exploring and refining complex mechanistic hypotheses by iterating computational evidence.
Authors
Dong Li, Sixuan Mi, Zihao Ye, Huan Xiong, Tao XU, Tong Zhu, Aijia Zhang, Junqi Gao, Kaiyan Zhang, Shijie Wang, Bowen Zhou, Yuqiang Li, Biqing Qi
Abstract
Unraveling reaction mechanisms is central to modern chemistry, yet automating these investigations remains challenging because computational workflows still rely heavily on expert intervention. Here we introduce ARCHE, an autonomous agentic system that integrates a general-purpose reasoning model, a domain-specialized computational chemistry model, and a structured tool registry to transform mechanistic inquiry into a scalable, self-validating process. ARCHE interprets scientific questions, generates and prioritizes mechanistic hypotheses, orchestrates computational workflows, and iteratively refines conclusions based on computed evidence within a closed loop. We validate its capabilities across three increasingly demanding scenarios: reconstructing stereocontrolling transition states and validating the corresponding reaction mechanism in a previously reported asymmetric catalytic reaction; proposing and validating a plausible radical pathway through iterative hypothesis refinement for a recently discovered but unpublished $α$-iodoboronate C-I cleavage reaction; and identifying a chemically interpretable descriptor that governs selectivity in nickel-catalysed migratory cross-coupling reactions. By coupling agentic reasoning with rigorous computational validation, ARCHE advances autonomous mechanistic discovery and establishes a foundation for broader machine-assisted chemical research. The code for ARCHE is publicly available at https://github.com/JetAstra/Arche-Harness.