{"ID":2843662,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10673","arxiv_id":"2511.10673","title":"Large language models in materials science and the need for open-source approaches","abstract":"Large language models (LLMs) are rapidly transforming materials science. This review examines recent LLM applications across the materials discovery pipeline, focusing on three key areas: mining scientific literature , predictive modelling, and multi-agent experimental systems. We highlight how LLMs extract valuable information such as synthesis conditions from text, learn structure-property relationships, and can coordinate agentic systems integrating computational tools and laboratory automation. While progress has been largely dependent on closed-source commercial models, our benchmark results demonstrate that open-source alternatives can match performance while offering greater transparency, reproducibility, cost-effectiveness, and data privacy. As open-source models continue to improve, we advocate their broader adoption to build accessible, flexible, and community-driven AI platforms for scientific discovery.","short_abstract":"Large language models (LLMs) are rapidly transforming materials science. This review examines recent LLM applications across the materials discovery pipeline, focusing on three key areas: mining scientific literature , predictive modelling, and multi-agent experimental systems. We highlight how LLMs extract valuable in...","url_abs":"https://arxiv.org/abs/2511.10673","url_pdf":"https://arxiv.org/pdf/2511.10673v1","authors":"[\"Fengxu Yang\",\"Weitong Chen\",\"Jack D. Evans\"]","published":"2025-11-10T00:05:20Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cond-mat.mtrl-sci\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}