ATLAS：用于自动化结构的原子翻译与语言
Building Atomic Structures from Natural Language
- State Key Laboratory of Materials for Integrated Circuits（集成电路材料国家重点实验室）
- Shanghai Institute of Microsystem and Information Technology（上海微系统与信息研究所）
- Chinese Academy of Sciences（中国科学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ATLAS是一个集成七模块的框架，通过组件代数和物理验证，将自然语言提示转化为有效的三维原子结构坐标，支持九大构建类别并具备自动优化循环。
AI中文摘要：
从自然语言描述自动生成三维原子结构仍然是一个持续的挑战，因为大型语言模型缺乏内在的几何推理能力。我们引入了ATLAS，一个整体框架，集成了七个模块化组件——从基于密度的结构分析器和基于JSON的语义桥，到确定性构建引擎、物理验证器和意图感知评分器——以将用户提示转换为物理上有效的坐标。构建引擎执行一个组件代数，涵盖命名结构、一元和二元操作（超胞、缩放、旋转、平移、并集、减法、交集）以及几何变量，而验证器强制执行周期性边界条件以及针对键合、配位、真空和组成的系统特定检查。ATLAS支持九大构建类别，包括异质结、表面、纳米粒子和缺陷，并配备了一个由评分驱动的自动细化循环，利用精选测试套件进行系统性的组件级改进。
英文摘要：
Large language models can write the input parameters of a materials simulation from a prompt, but they cannot build the atomic structure those parameters describe. A crystal, a surface slab or a mismatched interface must satisfy global constraints-periodicity along specific axes, a given vacuum thickness, a commensurate registry, sensible bond lengths. Generation one token at a time enforces none of them, and a violation is invisible in the output. We present ATLAS, a framework that makes structural construction scriptable. Seven components-analyzer, LLM skill, JSON format, build engine, validator, scorer and web interface-are organized around a component algebra of named structures and spaces. Every specification carries a check list, so a build is verified against the request rather than merely parsed from it, and builds are scored against the user's intent. Requests state physical sizes, and the engine computes the replication that reaches them. The translation is the one stochastic stage, and it is recorded, so a run replays with the model held fixed-which is what makes the framework's own behaviour measurable rather than merely observed. Fourteen structural classes are demonstrated, from bulk cells and nanoparticles through surfaces, defects and interfaces to amorphous networks and liquids. We outline how the same loop generates training sets for machine-learning force fields.
