Mastering Olympiad-Level Physics with Artificial Intelligence

TL;DR

This paper presents LOCA, an AI framework that decomposes complex physics problems into atomic steps, achieving near-perfect scores on Olympiad exams and surpassing human performance, advancing trustworthy AI in physics education and research.

Contribution

Introduction of LOCA, a novel AI reasoning framework that improves complex physics problem-solving by structured decomposition and iterative refinement.

Findings

LOCA scores 313/320 on CPhO, surpassing humans.

LOCA scores 28.6/30 on IPhO, showing strong generalizability.

LOCA outperforms baseline methods significantly.

Abstract

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.