Search papers, labs, and topics across Lattice.
This study leverages frontier language models to analyze reaction networks for discovering novel catalysts, addressing the limitations of traditional descriptor-based machine learning in complex electrochemical reactions. By employing a human-AI co-thinking framework, the authors identified key physical factors influencing product selectivity, leading to actionable hypotheses for catalyst design. The resulting copper-iron oxide catalyst exhibited a threefold increase in acetate selectivity compared to conventional Cu-rich baselines, demonstrating the efficacy of this mechanism-guided approach in materials discovery.
Frontier language models can uncover novel catalysts by pinpointing the physical levers that dictate reaction pathway competition, transforming catalyst design from trial-and-error to hypothesis-driven exploration.
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.
