Physics-R1: An Audited Olympiad Corpus and Released Verifiers for Visual Physics Reasoning

arXiv:2605.14040 · cs.CL · Submitted 2026-05-13 · Read on arXiv

cs.CL

Submitted: 2026-05-13

Updated: 2026-08-28

Code: https://github.com/shanyang-me/physics-r1-neurips2026

Project page: https://knzhou.github.io

Terminology

• Benchmark — 49× in this paper · explained in 2 episodes
• Ablation — 34× in this paper · explained in 1 episode
• Accuracy — 13× in this paper · explained in 1 episode
• Provenance — 8× in this paper · explained in 4 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Calibration — 5× in this paper · explained in 7 episodes
• LLM judge — 5× in this paper · explained in 2 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Failure Modes — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Entropy Collapse — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Alignment Scores — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Conservation Laws — 1× in this paper · explained in 3 episodes
• Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Croissant: A Metadata Format for ML-Ready Datasets
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
• MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• PhyX: Does Your Model Have the "Wits" for Physical Reasoning?
• HybridFlow: A Flexible and Efficient RLHF Framework
• Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?
• UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
• Group Sequence Policy Optimization
• OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering