mlsanityData to 14 Oct 2026

P1: Mastering Physics Olympiads with Reinforcement Learning

arXiv 2511.13612 ↗First posted 17 Nov 2025cs.LG cs.AI cs.CLcited by 8

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Recent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand against nature, not merely fit a rubric. Physics is the sharpest test of this shift, which binds symbols to reality in a fundamental way, serving as the cornerstone of most modern technologies. In this work, we manage to advance physics research by developing large language models with exceptional physics reasoning capabilities, especially excel at solving Olympiad-level physics problems. We introduce P1, a family of open-source physics reasoning models trained entirely through reinforcement learning (RL). Among them, P1-235B-A22B is the first open-source model with Gold-medal performance at the latest International Physics Olympiad (IPhO 2025), and wins 12 gold medals out of 13 international/regional physics competitions in 2024/2025. P1-30B-A3B also surpasses almost all other open-source models on IPhO 2025, getting a silver medal. Further equipped with an agentic framework PhysicsMinions, P1-235B-A22B+PhysicsMinions achieves overall No.1 on IPhO 2025, and obtains the highest average score over the 13 physics competitions. Besides physics, P1 models also present great performance on other reasoning tasks like math and coding, showing the great generalibility of P1 series.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 36 of its 56 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

36 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025TTRL: Test-Time Reinforcement Learning22 Apr

Other references · 35

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  7. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  8. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  9. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  10. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  12. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
23 more
  1. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  2. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  3. 2025Group Sequence Policy Optimizationcited by 835
  4. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 572
  5. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  6. 2025Process Reinforcement through Implicit Rewardscited by 504
  7. 2025Humanity's Last Examcited by 491
  8. 2025The Entropy Mechanism of Reinforcement Learning for Reasoning Language Modelscited by 485
  9. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 466
  10. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 344
  11. 2025MathArena: Evaluating LLMs on Uncontaminated Math Competitionscited by 297
  12. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 289
  13. 2025Learning to Reason without External Rewardscited by 210
  14. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  15. 2025Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivizationcited by 128
  16. 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
  17. 2025Towards Robust Mathematical Reasoningcited by 73
  18. 2025xVerify: Efficient Answer Verifier for Reasoning Model Evaluationscited by 55
  19. 2025AMO-Bench: Large Language Models Still Struggle in High School Math Competitionscited by 38
  20. 2025HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?cited by 19
  21. 2025Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025cited by 14
  22. 2025Scaling Physical Reasoning with the PHYSICS Datasetcited by 13
  23. 2025PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent Systemcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiadscited by 7
  2. 2026SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoningcited by 6
  3. 2026Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoningcited by 2
  4. 2026Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flatteningcited by 2
  5. 2025Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learningcited by 1
  6. 2026Perfect score on IPhO 2025 theory by Gemini agentcited by 1
  7. 2026PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?cited by 1
  8. 2026TEMPO: Scaling Test-time Training for Large Reasoning Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
  2. 2024Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback
  3. 2025PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems
  4. 2025PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level
  5. 2025Can Theoretical Physics Research Benefit from Language Agents?
  6. 2025UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
  7. 2025PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
  8. 2025Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs