# Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Sampling

arXiv: https://arxiv.org/abs/2509.00768 · HTML: https://mlsanity.com/paper/2509.00768/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce](https://mlsanity.com/paper/2504.11343/) (2025)
- [LLMatDesign: Autonomous Materials Discovery with Large Language Models](https://mlsanity.com/paper/2406.13163/) (2024)
- [Materials Property Prediction with Uncertainty Quantification: A Benchmark Study](https://mlsanity.com/paper/2211.02235/) (2022)
- [Inverse deep learning methods and benchmarks for artificial electromagnetic material design](https://mlsanity.com/paper/2112.10254/) (2021)
- [AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners](https://mlsanity.com/paper/2505.16322/) (2025)
- [From Tokens to Materials: Leveraging Language Models for Scientific Discovery](https://mlsanity.com/paper/2410.16165/) (2024)
- [Artifacts of Numerical Integration in Learning Dynamical Systems](https://mlsanity.com/paper/2507.14491/) (2025)
- [Multi-fidelity Bayesian Data-Driven Design of Energy Absorbing Spinodoid Cellular Structures](https://mlsanity.com/paper/2507.22079/) (2025)

## Built on by (most cited first, 1 of 1)

- [Physics as the label for measuring and correcting materials reasoning in multimodal models](https://mlsanity.com/paper/2609.12181/) (2026)

## Abstract (arXiv)

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.