AI RESEARCH
AI-Driven Expansion and Application of the Alexandria Database
arXiv CS.AI
•
ArXi:2512.09169v2 Announce Type: replace-cross We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches. By combining the Matra-Genoa generative model, Orb-v2 universal machine learning interatomic potential, and ALIGNN graph neural network for energy prediction, we generated 119M candidate structures and added 1.3M DFT-validated compounds to the ALEXANDRIA database, including 74K new stable materials.