发表机构
Shanghai Artificial Intelligence Laboratory; Institute for Advanced Study in Mathematics, Harbin Institute of Technology; School of Mathematics, Harbin Institute of Technology; School of Chemistry and Molecular Engineering, East China Normal University; Department of Chemistry, Fudan University; Department of Electronic Engineering, Tsinghua University; School of Chemical Science and Engineering, Tongji University（上海人工智能实验室; 哈尔滨工业大学数学研究院; 哈尔滨工业大学数学学院; 华东师范大学化学与分子工程学院; 复旦大学化学系; 清华大学电子工程系; 同济大学化学科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ARCHE是一个自主智能体系统，结合推理模型与计算化学工具，自动生成、验证并精炼反应机理假设，在多个复杂反应中实现自主机理发现。
AI 中文摘要
揭示反应机理是现代化学的核心，然而自动化这些研究仍具挑战性，因为计算工作流高度依赖专家干预。在此，我们提出ARCHE，一个自主智能体系统，它整合了通用推理模型、领域专用的计算化学模型以及结构化工具注册表，将机理探究转变为可扩展、自验证的过程。ARCHE解读科学问题，生成并优先排序机理假设，编排计算工作流，并在闭环中基于计算证据迭代精炼结论。我们通过三个难度递增的场景验证其能力：重建立体控制过渡态并验证先前报道的不对称催化反应中相应的反应机理；通过迭代假设精炼，为最近发现但未发表的α-碘代硼酸酯C-I键断裂反应提出并验证合理的自由基路径；以及识别控制镍催化迁移交叉偶联反应选择性的化学可解释描述符。通过将智能体推理与严格的计算验证相结合，ARCHE推进了自主机理发现，并为更广泛的机器辅助化学研究奠定了基础。ARCHE的代码公开可获取于该https URL。
英文摘要
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and validating a plausible radical pathway through iterative hypothesis refinement for a recently discovered but unpublished $α$-iodoboronate C-I cleavage reaction; and identifying a chemically interpretable descriptor that governs selectivity in nickel-catalysed migratory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.
CommentsThis paper has been submitted to Nature Communications
