Awesome Auto Research Hub Papers · Datasets · Projects
← Back to papers

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

arXiv 2025 46.1 method

TLDR

Introduces Physics-aware Rejection Sampling (PaRS) to train reasoning LLMs for accurate, calibrated, and physically admissible property prediction in materials discovery.

Reasoning

Strengths: Novel domain-aware training method (PaRS) that improves accuracy, calibration, and reduces physics violations; clear methodology and evaluation against baselines. Weaknesses: Limited to property prediction tasks; no real-world experimental validation or deployment in closed-loop systems is demonstrated.

Read-first score

Read-first score 46.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 40.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,experiment,result

Topical relevance 42%
33.3

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 10.

Keyword Scores

automated scientific discovery
8
AI for scientific research
7
scientific discovery agent
6
AI scientist
5
automated research
4
research automation
4
autonomous research agent
3
automated experimentation
2
experiment design agent
1
literature review agent
0
survey generation
0
paper writing agent
0

Deep Analysis

Innovations

  • Physics-aware Rejection Sampling (PaRS) for training-time selection of reasoning traces
  • Incorporation of physical admissibility (consistency with fundamental physics and numerical closeness) into trace selection criteria
  • Lightweight halting mechanism to control compute during trace selection

Methodology

A teacher-student framework where a larger teacher model generates reasoning traces, and PaRS selects traces that are physically consistent and numerically close to targets, with halting to limit compute. The student model is fine-tuned on these selected traces and evaluated under matched token budgets against rejection sampling baselines.

Key Results

PaRS improves accuracy and calibration, reduces physics-violation rates, and lowers sampling cost compared to baselines using binary correctness or learned preference signals.

Tags

AImtrl-sciCL