The discovery of new energetic materials remains a pressing challenge hindered by limited availability of high-quality data. To address this, we have developed generative molecular language models that have been pretrained on extensive chemical data and then fine-tuned with curated energetic materials datasets. This transfer-learning strategy extends the chemical language model capabilities beyond the pharmacological space in which they have been predominantly developed, offering a framework applicable to other data-spare discovery problems. Furthermore, we discuss the benefits of fragment-based molecular encodings for chemical language models, in particular in constructing synthetically accessible structures. Together, these advances provide a foundation for accelerating the design of next-generation energetic materials with demanding performance requirements.
@article{arxiv.2604.03304,
title = {Generative Chemical Language Models for Energetic Materials Discovery},
author = {Andrew Salij and R. Seaton Ullberg and Megan C. Davis and Marc J. Cawkwell and Christopher J. Snyder and Cristina Garcia Cardona and Ivana Matanovic and Wilton J. M. Kort-Kamp},
journal= {arXiv preprint arXiv:2604.03304},
year = {2026}
}