Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
Dong Li, Biqing Qi and colleagues (Shanghai AI Laboratory with Harbin Institute of Technology and others) build ARCHE, an agent that proposes reaction mechanisms, runs computational chemistry workflows to test them and revises conclusions from the computed evidence.
Ask this paper
System: A general reasoning model, a computational chemistry model and a structured tool registry, operating in a closed loop of hypothesis, computation and refinement.
Case one: Reconstructs stereocontrolling transition states and validates the mechanism of a published asymmetric catalytic reaction.
Case two: Proposes and validates a radical pathway for a recently discovered, unpublished alpha-iodoboronate C-I cleavage reaction.
Case three: Identifies an interpretable descriptor that governs selectivity in nickel-catalysed migratory cross-coupling. Code is public.
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and validating a plausible radical pathway through iterative hypothesis refinement for a recently discovered but unpublished $α$-iodoboronate C-I cleavage reaction; and identifying a chemically interpretable descriptor that governs selectivity in nickel-catalysed migratory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.