Over the last decades, excellent computational chemistry tools have been developed. Their full potential has not yet been reached as most are challenging to learn and exist in isolation. Recently, large-language models (LLMs) have 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 17 expert-designed tools, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned the syntheses of an insect repellent, three organocatalysts, as well as other relevant molecules. Our evaluation, including both LLM and expert 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 Chemcrow's performance. There is a significant risk of misuse of tools like ChemCrow, and we discuss their potential harms. Employed responsibly, our work 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. A subset of the code is publicly available at \url{https://github.com/ur-whitelab/chemcrow-public}.

翻译：过去几十年中，优秀的计算化学工具被不断开发，但其全部潜力尚未得以充分发挥，原因在于多数工具学习门槛高且彼此孤立存在。近年来，大型语言模型（LLM）在跨领域任务中展现出强大性能，但在化学相关问题上仍力有不逮。此外，这些模型缺乏对外部知识源的访问能力，限制了其在科学应用中的实用性。本研究提出ChemCrow——一种面向有机合成、药物发现与材料设计任务的LLM化学智能体。通过整合17个专家设计的工具，ChemCrow增强了LLM在化学领域的表现，并催生了新的能力。我们的智能体自主完成了驱虫剂、三种有机催化剂及其他相关分子的合成路线规划。基于LLM与专家评估的结果表明，ChemCrow能有效自动化处理多样化的化学任务。令人惊讶的是，我们发现作为评估者的GPT-4无法区分明显错误的GPT-4输出与ChemCrow的性能表现。诸如ChemCrow这类工具存在重大的滥用风险，我们对其潜在危害进行了讨论。在负责任地使用前提下，我们的工作不仅能为专业化学家提供辅助并降低非专业人士的使用门槛，更能通过弥合实验化学与计算化学之间的鸿沟，推动科学进步。部分代码已在\url{https://github.com/ur-whitelab/chemcrow-public}公开。