MétaCan
Menu
Back to cohort
Record W7117242258 · doi:10.48550/arxiv.2512.19799

PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research

2025· preprint· W7117242258 on OpenAlexaff
Tingjia Miao, Jiawen Dai, Jingkun Liu, M. Zhang, Wenkai Jin, Yuwen Du, Tian Jin, Xianghe Pang, Tu Guo, Zhengliang ZHANG, Yunjie Huang, Shangheng Chen, Rui Ye, Yuzhi Zhang, Linfeng Zhang, Kun Chen, Wei Wang, Weinan E, Siheng Chen

Bibliographic record

VenuearXiv (Cornell University) · 2025
Typepreprint
Language
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsLimitingComputationReliability (semiconductor)Computational modelUncertainty quantificationOpen research

Abstract

fetched live from OpenAlex

Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires deep domain expertise, long-horizon reasoning, and reliable numerical computation. We introduce PRL-Bench, a research-reproduction benchmark adapted from 100 Physical Review Letters papers across major areas of modern physics. PRL-Bench distills realistic research workflows into traceable tasks with explicit intermediate artifacts and diverse evaluation rubrics; each task is estimated by domain experts to require more than six hours for a specialized PhD student to reproduce independently. Evaluations show that existing agents remain unreliable on extended research workflows. We therefore present PhysMaster, a scientific agent combining adaptive MCTS-based multi-trajectory exploration with hierarchical memory to improve long-horizon robustness and knowledge accumulation. PhysMaster achieves the highest overall PRL-Bench score of 51.08, outperforming Codex, OpenHands, OpenClaw, and ReAct, and yields relative improvements of 14.13 percent to 93.38 percent across backbone models. Error analysis shows that PhysMaster substantially reduces failures from incomplete long-horizon execution, while remaining bottlenecks lie in physics knowledge and analytical reasoning. Together, PRL-Bench and PhysMaster provide a rigorous benchmark and effective system for advancing autonomous AI research in frontier physics.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.007
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.009
Threshold uncertainty score0.030

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.007
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.003
Open science0.0020.005
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0090.004

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.290
GPT teacher head0.359
Teacher spread0.070 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicScientific Computing and Data ManagementFrench-language works237,207