Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses

2026-07-08

AI Summary

Traditional approaches struggle to decipher the dynamic branching mechanisms governing product selectivity in complex electrocatalytic reactions, often relying on trial-and-error strategies or static descriptors that lack end-to-end topological analysis of reaction pathways. This work proposes a human–AI collaborative reasoning framework that, for the first time, integrates a constrained frontier language model with explicit reaction networks, incorporating network invariance constraints and fundamental electrocatalytic principles to shift from statistical prediction toward mechanism-driven hypothesis generation. The approach identifies key regulatory levers—including local alkalinity, iron doping, and proton donor accessibility—and successfully predicts a novel pathway for acetate formation. Guided by these insights, Cu–Fe oxide catalysts were synthesized, achieving a threefold enhancement in acetate selectivity during CO₂ electroreduction compared to conventional Cu-based controls.

Abstract

Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computationally intensive screening. In complex reactions such as electrochemical carbon dioxide reduction, product selectivity is governed by dynamic interfacial, electrolyte, and potential factors as well as kinetic pathway competition. Conventional descriptor-based machine learning and computational potentials struggle to resolve these mechanistic branch points, primarily relying on static ground-state descriptors or bulk structural correlations rather than end-to-end topological pathway analysis. Here, we show that frontier language models, when strictly constrained to reason over explicit reaction networks, can discover novel catalysts by identifying the physical levers that govern pathway competition. We developed a human-AI co-thinking framework that enforces network invariance to extract testable hypotheses from complex chemical graphs. Applied to CO2 electroreduction, the framework identified ketene desorption and hydroxide capture as the acetate-forming pathway, and predicted a distinct adsorbed CO and CH2 coupling route to ketene. By isolating actionable control levers, specifically local alkalinity, controlled iron incorporation, and restricted interfacial proton-donor accessibility, the framework guided the prospective synthesis of a copper-iron oxide catalyst demonstrating a threefold increase in acetate selectivity over matched Cu-rich baselines. This mechanism-guided reasoning architecture shifts the computational paradigm from retrospective statistical prediction to forward-looking hypothesis generation, providing a broadly applicable blueprint for mechanism-guided materials discovery.

Problem

• catalyst selectivity
• reaction network
• CO2 electroreduction
• mechanistic branching
• materials discovery

Innovation

• reaction-network reasoning
• frontier language models
• mechanism-guided discovery
• catalyst selectivity
• CO2 electroreduction