Augmenting large language models with chemistry tools

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent and three organocatalysts and guided the discovery of a novel chromophore. Our evaluation, including both…

• NS
  National Science Foundation

  Award: 1751471
• ÉP
  École Polytechnique Fédérale de Lausanne
• SN
  Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

  Award: 180544
• NI
  National Institutes of Health

  Award: R35GM137966
• NI
  National Institute of General Medical Sciences

  Award: R35GM137966