Artificial intelligence (AI) for reaction condition optimization has become
an important topic in the pharmaceutical industry, given that a data-driven AI
model can assist drug discovery and accelerate reaction design. However,
existing AI models lack the chemical insights and real-time knowledge
acquisition abilities of experienced human chemists. This paper proposes a
Large Language Model (LLM) empowered AI agent to bridge this gap. We put forth
a novel three-phase paradigm and applied advanced intelligence-enhancement
methods like in-context learning and multi-LLM debate so that the AI agent can
borrow human insight and update its knowledge by searching the latest chemical
literature. Additionally, we introduce a novel Coarse-label Contrastive
Learning (CCL) based chemical fingerprint that greatly enhances the agent's
performance in optimizing the reaction condition. With the above efforts, the
proposed AI agent can autonomously generate the optimal reaction condition
recommendation without any human interaction. Further, the agent is highly
professional in terms of chemical reactions. It demonstrates close-to-human
performance and strong generalization capability in both dry-lab and wet-lab
experiments. As the first attempt in the chemical AI agent, this work goes a
step further in the field of "AI for chemistry" and opens up new possibilities
for computer-aided synthesis planning.

药物行业的人工智能（AI）反应条件优化成为一个重要的话题，该数据驱动的 AI 模型可以帮助药物研发并加速反应设计。本文提出了一个大型语言模型（LLM）强化的 AI 代理，以填补现有 AI 模型不具备化学洞察力和获取实时知识的缺陷。通过引入先进的智能增强方法，如上下文学习和多 LLM 辩论，AI 代理可以借鉴人类的洞察力并通过搜索最新的化学文献来更新知识。此外，我们引入了一种基于粗略标签对比学习（CCL）的化学指纹，大大提高了代理在优化反应条件方面的性能。经过以上努力，所提出的 AI 代理能够自主地生成最佳的反应条件推荐而不需要任何人类交互。此外，该代理在化学反应方面表现出高度专业性，同时在干实验室和湿实验室实验中显示出接近人类的性能和强大的泛化能力。作为化学 AI 代理的首次尝试，本研究在 “化学 AI” 领域取得了进一步的进展，并为计算辅助合成计划开启了新的可能性。