The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.

翻译：新催化剂的发现对于设计更高效的化学过程以实现可持续未来至关重要。我们提出了一种人工智能引导的计算筛选框架，该框架将语言推理与基于三维原子表征的量子化学反馈相结合。我们的方法将催化剂发现形式化为一个不确定环境，其中智能体通过迭代结合大型语言模型得出的假设与基于原子图的图神经网络反馈，主动搜索高效催化剂。在中间搜索步骤中识别的催化剂需基于空间取向、反应路径和稳定性进行结构评估。基于吸附能和能垒的评分函数引导LLM知识空间中的探索，朝向能量有利的高效催化剂方向。我们提出了无需人机输入即可自动引导探索的规划方法，其性能可与专家枚举的化学描述符方法相媲美。通过将语言引导推理与计算化学反馈相结合，我们的工作开创了AI驱动的可信催化剂发现新范式。