Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models

Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, Changshui Zhang


Abstract
Physics problems constitute a significant aspect of reasoning, necessitating complicated reasoning ability and abundant physics knowledge. However, existing large language models (LLMs) frequently fail due to a lack of knowledge or incorrect knowledge application. To mitigate these issues, we propose Physics Reasoner, a knowledge-augmented framework to solve physics problems with LLMs. Specifically, the proposed framework constructs a comprehensive formula set to provide explicit physics knowledge and utilizes checklists containing detailed instructions to guide effective knowledge application. Namely, given a physics problem, Physics Reasoner solves it through three stages: problem analysis, formula retrieval, and guided reasoning. During the process, checklists are employed to enhance LLMs’ self-improvement in the analysis and reasoning stages. Empirically, Physics Reasoner mitigates the issues of insufficient knowledge and incorrect application, achieving state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.
Anthology ID:
2025.coling-main.747
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11274–11289
Language:
URL:
https://aclanthology.org/2025.coling-main.747/
DOI:
Bibkey:
Cite (ACL):
Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, and Changshui Zhang. 2025. Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 11274–11289, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models (Pang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.747.pdf