基于基元语言的智能体AI晶体结构设计

中文摘要 AI 辅助

数据驱动的材料发现在插值时比外推更可靠，且很少能发现新的结构类型。我们提出MatEvolve，一款用于晶体设计的智能体AI框架，该框架会提出每个候选结构并给出明确理由，再对其进行测试。智能体以可解释的“基元语言”进行推理，将每个晶体描述为“基元轮廓”，该轮廓刻画了构成晶体的重复几何模式——即“基元”。基元轮廓不仅是对材料的描述，也是材料设计的媒介：智能体编辑该轮廓并根据修改后的轮廓构建晶体，最具前景的候选结构会通过第一性原理计算进行验证。将其应用于贫稀土永磁体设计时，MatEvolve（基于最先进的语言模型Claude Fable 5构建，未进行微调）在相同验证预算下，发现新结构原型的频率是生成模型的三倍以上，且目标磁体的比例相当。除设计外，分析所发现晶体的人类可读轮廓还能揭示结构-性能关系。

英文摘要

Data-driven materials discovery interpolates more reliably than it extrapolates and seldom reaches new structure types. We present MatEvolve, an agentic-AI framework designing crystals, proposing each candidate with a stated rationale and testing it. The agent reasons in an interpretable \emph{language of motifs}, writing each crystal as a \emph{motif profile} that describes the recurring geometric patterns---the \emph{motifs}---composing it. The motif profile serves not merely as a description of a material but as the medium for material design: the agent edits the profile and constructs a crystal from the modified one, and the most promising candidates are validated by first-principles calculation. Applied to the design of rare-earth-lean permanent magnets, MatEvolve---built on the state-of-the-art language model Claude Fable~5 without fine-tuning---reaches new structural prototypes more than three times as often as generative models under an equal validation budget, at a comparable on-target-magnet rate. Beyond design, analysing the discovered crystals' human-readable profiles reveals structure--property relationships.

发表机构

• Japan Advanced Institute of Science and Technology（日本先进科学技术学院）
• Institute of Science Tokyo（东京科学大学）
• The Institute of Statistical Mathematics（统计数理研究所）
• Tohoku University（东北大学）

机构由 AI 辅助整理，请以论文原文为准。