AI Reasoning Models for Problem Solving in Physics
2025/08/28 by Amir Bralin, N. Sanjay Rebello, Bralin, Amir +1 · 4 voices
#physics.ed-ph
paper · pdf · doi:10.48550/arxiv.2508.20941
Abstract
Reasoning models are the new generation of Large Language Models (LLMs) capable of complex problem solving. Their reliability in solving introductory physics problems was tested by evaluating a sample of n = 5 solutions generated by one such model -- OpenAI's o3-mini -- per each problem from 20 chapters of a standard undergraduate textbook. In total, N = 408 problems were given to the model and N x n = 2,040 generated solutions examined. The model successfully solved 94% of the problems posed, excelling at the beginning topics in mechanics but struggling with the later ones such as waves and thermodynamics.
Citations
Discussions
- #arXiv AI Reasoning Models for Problem Solving in Physics arxiv.org/abs/2508.20941 5 GPT o3-mini solutions per 408 problems from 20 chapters of a standard undergraduate textbook. The model solved 94%, [bsky, 5 points, 0 comments]
- #arXiv AI Reasoning Models for Problem Solving in Physics https://arxiv.org/abs/2508.20941 5 GPT o3-mini solutions per 408 problems from 20 chapters of a standard undergraduate textbook. The model sol [bsky, 0 points, 0 comments]
- Amir Bralin, N. Sanjay Rebello: AI Reasoning Models for Problem Solving in Physics https://arxiv.org/abs/2508.20941 https://arxiv.org/pdf/2508.20941 https://arxiv.org/html/2508.20941 [bsky, 0 points, 0 comments]
- # arXiv AI Reasoning Models for Problem Solving in Physics https:// arxiv.org/abs/2508.20941 5 GPT o3-mini solutions per 408 problems from 20 chapters of a standard undergraduate textbook. The model s [mastodon, 0 points, 0 comments]
Related