arXiv 论文提出自主发现的 PRIS 晶体结构合定律,可解释筛查并大幅削减 DFT 验证量
Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening
AI 导读
论文作者团队用智能体生成、测试并驳斥两百万条候选定律,发现八条无机结构合定律(PRIS),编码短程排斥、静电平衡、键价守恒等五种物理机制。
推荐理由
论文用智能体主动驳斥两百万条候选定律发现 PRIS 规则,把晶体筛选从通过与否推进到给出化学层面的失败原因。
正文 · 原文
Abstract:Generative models and autonomous agents now propose candidate inorganic crystals by the million, yet most screens test little beyond a minimum-distance cutoff and give no chemical reason for failure. For nearly a century, Pauling's rules have served as the main empirical theory of crystal-structure stability, but they remain qualitative and idealized, leading to only 6.5% of known ionic crystals satisfying rules 2--5 simultaneously. Here our agents generate, test and refute two million candidate laws to discover eight Plausibility Rules for Inorganic Structures (PRIS). These laws encode five physical mechanisms: short-range repulsion, ionic contact and packing, electrostatic balance, bond-valence conservation and crystallographic site simplicity. Experimental structures satisfy the PRIS law sets in 82--99% of cases, and the strictest set detects 87.9% of artificially damaged structures, far above the 1.6--3.2% of conventional distance cutoffs. Although derived without synthesis labels, PRIS plausibility is highly linearly correlated with synthesizability, and a continuous PRIS-derived synthesis score (PSS) explainably filters out 83.7% of hard-to-synthesize structures while retaining 80.7% of experimental structures. In an inverse-design task targeting ultra-incompressible crystals, explainable screening by PRIS and PSS cuts the density functional theory (DFT) validation queue by up to 67.3% while retaining 99.2% of the DFT-verified target candidates. Beyond screening, PRIS traces GNoME's low-symmetry excess to artificial element ordering and identifies falsified crystal structures. PRIS moves screening from a pass-or-fail verdict to a chemical reason for failure, showing that autonomous agents can discover, by active refutation, physicochemical laws that guide calculations and experiments.
| Subjects: | Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.01209 [cond-mat.mtrl-sci] |
| (or arXiv:2609.01209v2 [cond-mat.mtrl-sci] for this version) | |
| https://doi.org/10.48550/arXiv.2609.01209 arXiv-issued DOI via DataCite |
Submission history
From: Lixue Cheng [view email]
[v1]
Tue, 1 Sep 2026 13:14:52 UTC (1,685 KB)
[v2]
Wed, 18 Nov 2026 14:45:14 UTC (1,789 KB)
来源:arXiv cs.AI · arxiv.org