{"ID":2876202,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00768","arxiv_id":"2509.00768","title":"Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Sampling","abstract":"AI-driven materials discovery that couples automated experimentation with algorithmic decision-making requires process aware recipe to property predictors that are accurate, calibrated, and physically admissible. We approach this as a reasoning problem with large reasoning models (LRMs). To instill reasoning capability into language models, we curate reasoning traces from a teacher model to train a student model. However, most training pipelines select reasoning traces using binary correctness or learned preference signals that poorly reflect physical admissibility. We introduce Physics-aware Rejection Sampling (PaRS), a training-time trace selection scheme that favors traces consistent with fundamental physics and numerically close to targets, with lightweight halting to control compute. We instantiate our framework with a large student model fine-tuned on traces synthesized by a larger teacher model, and evaluate under matched token budgets against various rejection sampling baselines. Our method improves accuracy and calibration, reduces physics-violation rates, and lowers sampling cost relative to baselines. These results indicate that modest, domain-aware constraints combined with trace-level selection provide a practical path toward reliable, efficient LRMs for process-aware property prediction and closed-loop materials design.","short_abstract":"AI-driven materials discovery that couples automated experimentation with algorithmic decision-making requires process aware recipe to property predictors that are accurate, calibrated, and physically admissible. We approach this as a reasoning problem with large reasoning models (LRMs). To instill reasoning capability...","url_abs":"https://arxiv.org/abs/2509.00768","url_pdf":"https://arxiv.org/pdf/2509.00768v2","authors":"[\"Lee Hyun\",\"Sohee Yoon\",\"Jinwoo Park\",\"Sue In Chae\",\"Seongeon Park\",\"Jooyeon Ahn\",\"Yebin Jung\",\"Youjung Chung\",\"Hogeun Chang\",\"Sujin Park\",\"Myeonginn Kang\",\"Jina Kim\",\"Ho-Gyeong Kim\",\"Myeonghun Jeong\"]","published":"2025-08-31T09:46:20Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cond-mat.mtrl-sci\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}