mlsanityData to 14 Oct 2026

Mastering Olympiad-Level Physics with Artificial Intelligence

arXiv 2511.10515 ↗First posted 13 Nov 2025cs.CL cs.AI physics.ed-phcited by 1

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Olympiad-level physics problem-solving significantly challenges both humans and artificial intelligence (AI), as it requires integrating appropriate modeling, application of physical principles, and precise calculation within long reasoning processes. In this paper, we introduce LOCA (LOgical Chain Augmentation), an AI agent framework designed for complex physics reasoning. LOCA decomposes long reasoning into serialized atomic and verifiable steps, refining the solution through an augment-review loop. We evaluate LOCA on the 2025 Chinese Physics Olympiad (CPhO) theory examination, a rigorous testbed renowned for its depth and complexity. The framework achieves a near-perfect score of 313 out of 320 points, significantly surpassing the top human competitor and other baseline methods. Furthermore, LOCA attains a near-perfect score of 28.6 out of 30 on the IPhO 2025 examination, demonstrating its strong generalizability across different contexts. Our work points toward the development of trustworthy AI partners in both research and education.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 38 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

34 of 38 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025PhysicsEval: Inference-Time Techniques to Improve the Reasoning Proficiency of Large Language Models on Physics Problems31 Jul
  2. 2025ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems7 Jul
  3. 2025PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models22 Apr
  4. 2025Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics19 Feb
  5. 2025PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning17 Feb
  6. 2025UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models1 Feb
  7. 2024Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models18 Dec
  8. 2024Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents1 Dec

Other references · 26

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2025Qwen3 Technical Reportcited by 8,820
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  11. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
14 more
  1. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  2. 2023PaLM 2 Technical Reportcited by 1,162
  3. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  4. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  5. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  6. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
  7. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  8. 2025PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understandingcited by 160
  9. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 50
  10. 2024Large Language Models have Intrinsic Self-Correction Abilitycited by 46
  11. 2024SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Modelscited by 39
  12. 2025Physics: Benchmarking Foundation Models on University-Level Physics Problem Solvingcited by 31
  13. 2025Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025cited by 14
  14. 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: 2026: 1.

1 paper.

  1. 2026Language models can notice an impossible engineering problem yet still report it as solvedcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025P1: Mastering Physics Olympiads with Reinforcement Learning
  2. 2026TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving
  3. 2025PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level
  4. 2025Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving
  5. 2025PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
  6. 2025Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning
  7. 2025SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
  8. 2026Riemann-Bench: A Benchmark for Moonshot Mathematics