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.
@article{arxiv.2511.10515,
title = {Mastering Olympiad-Level Physics with Artificial Intelligence},
author = {Dong-Shan Jian and Xiang Li and Chen-Xu Yan and Hui-Wen Zheng and Zhi-Zhang Bian and You-Le Fang and Ren-Xi He and Jing-Tian Zhang and Ce Meng and Ling-Shi Meng and Bing-Rui Gong and Sheng-Qi Zhang and Yan-Qing Ma},
journal= {arXiv preprint arXiv:2511.10515},
year = {2026}
}
Comments
8 pages, 3 figures, Content from the previous article 2510.01249 is included