LOCA-R: Near-Perfect Performance on the Chinese Physics Olympiad 2025
This addresses the challenge of advanced physics problem-solving for AI, with incremental improvements to an existing framework.
The paper tackled solving complex physics problems in the Chinese Physics Olympiad 2025 using LOCA-R, achieving a near-perfect score of 313 out of 320 points and surpassing human competitors and baselines.
Olympiad-level physics problem-solving presents a significant challenge for both humans and artificial intelligence (AI), as it requires a sophisticated integration of precise calculation, abstract reasoning, and a fundamental grasp of physical principles. The Chinese Physics Olympiad (CPhO), renowned for its complexity and depth, serves as an ideal and rigorous testbed for these advanced capabilities. In this paper, we introduce LOCA-R (LOgical Chain Augmentation for Reasoning), an improved version of the LOCA framework adapted for complex reasoning, and apply it to the CPhO 2025 theory examination. LOCA-R achieves a near-perfect score of 313 out of 320 points, solidly surpassing the highest-scoring human competitor and significantly outperforming all baseline methods.