LLM-Driven Discovery of High-Entropy Catalysts via Retrieval-Augmented Generation

ArXi:2603.15712v1 Announce Type: cross CO2 reduction requires efficient catalysts, yet materials discovery remains bottlenecked by 10-20 year development cycles requiring deep domain expertise. This paper nstrates how large language models can assist the catalyst discovery process by helping researchers explore chemical spaces and interpret results when augmented with retrieval-based grounding. We