Preprint
Aug 2026
Interpretable physics-informed retrieval-augmented generation language model for end-to-end inorganic crystal synthesis planning
An interpretable Physics-Informed Retrieval-Augmented Generation Language Model for end-to-end inorganic crystal synthesis planning that achieves 91.4% accuracy in synthesis-method prediction and generalizes to materials reported after the knowledge cutoff.
Wei-Jian Jiang, Ye-Nan Sha, Hui Guo et al.
· 0 citations