Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.10515 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915803032453120 |
|---|---|
| author | Jian, Dong-Shan Li, Xiang Yan, Chen-Xu Zheng, Hui-Wen Bian, Zhi-Zhang Fang, You-Le He, Ren-Xi Zhang, Jing-Tian Meng, Ce Meng, Ling-Shi Gong, Bing-Rui Zhang, Sheng-Qi Ma, Yan-Qing |
| author_facet | Jian, Dong-Shan Li, Xiang Yan, Chen-Xu Zheng, Hui-Wen Bian, Zhi-Zhang Fang, You-Le He, Ren-Xi Zhang, Jing-Tian Meng, Ce Meng, Ling-Shi Gong, Bing-Rui Zhang, Sheng-Qi Ma, Yan-Qing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_10515 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mastering Olympiad-Level Physics with Artificial Intelligence Jian, Dong-Shan Li, Xiang Yan, Chen-Xu Zheng, Hui-Wen Bian, Zhi-Zhang Fang, You-Le He, Ren-Xi Zhang, Jing-Tian Meng, Ce Meng, Ling-Shi Gong, Bing-Rui Zhang, Sheng-Qi Ma, Yan-Qing Computation and Language Artificial Intelligence Physics Education 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. |
| title | Mastering Olympiad-Level Physics with Artificial Intelligence |
| topic | Computation and Language Artificial Intelligence Physics Education |
| url | https://arxiv.org/abs/2511.10515 |