Large-language models (LLMs) have recently shown strong performance in tasks across domains, but struggle with chemistry-related problems. Moreover, these models lack access to external knowledge sources, limiting their usefulness in scientific applications. In this study, we introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery, and materials design. By integrating 13 expert-designed tools, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our evaluation, including both LLM and expert human assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Surprisingly, we find that GPT-4 as an evaluator cannot distinguish between clearly wrong GPT-4 completions and GPT-4 + ChemCrow performance. There is a significant risk of misuse of tools like ChemCrow and we discuss their potential harms. Employed responsibly, ChemCrow not only aids expert chemists and lowers barriers for non-experts, but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.
View on arXiv