Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening
Abstract
Crystal generators and tool-using agents propose structures faster than density functional theory (DFT) energy and phonon calculations or experiments can assess them. Deciding which candidates merit expensive assessment is therefore the bottleneck, yet most screens test little beyond atomic overlap and give no chemical reason for failure. Here, our agents generate, test and actively refute two million candidate laws, leaving eight Plausibility Rules for Inorganic Structures (PRIS). These laws encode five mechanisms: short-range repulsion, ionic contact and packing, electrostatic balance, bond-valence conservation and crystallographic site complexity. Experimental structures satisfy our law sets at 82--99%, but satisfy Pauling's rules 2--5 together at only 6.5%. The strictest set detects 87.9% of damaged crystal structures, whereas distance cutoffs detect only 1.6--3.2%. PRIS plausibility is linearly correlated with synthesizability, so the PRIS-derived synthesis score (PSS) explainably screens 83.7% of hard-to-synthesize structures while retaining 80.7% of experimental structures. In a property-conditioned inverse-design run, PRIS and PSS can reduce the DFT validation queue by up to 67.3% and keep 99.2% of the candidates whose DFT-validated bulk moduli reach the design target. Beyond screening, PRIS explains why GNoME remains enriched in rare low-symmetry structures and reveals how wrong-element assignments in falsified crystal reports hide behind plausible coordinates. 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.
Related
- False-science induction in autonomous scientific discovery
- Autonomous discovery of reaction networks from active-learning-driven reactive molecular dynamics
- Divergent strategies and convergent outcomes in autonomous materials discovery
- Autonomous phase discovery
- From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
BibTeX
@misc{song2026autonomous,
title = {{Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening}},
author = {Zhilong Song and Lixue Cheng},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01209},
eprint = {2609.01209},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01209},
}
RIS
TY - UNPB
TI - Autonomous discovery of new structure-plausibility laws for explainable and rapid crystal diagnosis and screening
AU - Zhilong Song
AU - Lixue Cheng
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01209
UR - https://arxiv.org/abs/2609.01209
AB - Crystal generators and tool-using agents propose structures faster than density functional theory (DFT) energy and phonon calculations or experiments can assess them. Deciding which candidates merit expensive assessment is therefore the bottleneck, yet most screens test little beyond atomic overlap and give no chemical reason for failure. Here, our agents generate, test and actively refute two million candidate laws, leaving eight Plausibility Rules for Inorganic Structures (PRIS). These laws encode five mechanisms: short-range repulsion, ionic contact and packing, electrostatic balance, bond-valence conservation and crystallographic site complexity. Experimental structures satisfy our law sets at 82--99%, but satisfy Pauling's rules 2--5 together at only 6.5%. The strictest set detects 87.9% of damaged crystal structures, whereas distance cutoffs detect only 1.6--3.2%. PRIS plausibility is linearly correlated with synthesizability, so the PRIS-derived synthesis score (PSS) explainably screens 83.7% of hard-to-synthesize structures while retaining 80.7% of experimental structures. In a property-conditioned inverse-design run, PRIS and PSS can reduce the DFT validation queue by up to 67.3% and keep 99.2% of the candidates whose DFT-validated bulk moduli reach the design target. Beyond screening, PRIS explains why GNoME remains enriched in rare low-symmetry structures and reveals how wrong-element assignments in falsified crystal reports hide behind plausible coordinates. 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.
ER -