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

arXiv: https://arxiv.org/abs/2412.13791 · HTML: https://mlsanity.com/paper/2412.13791/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [Self-Evaluation Guided Beam Search for Reasoning](https://mlsanity.com/paper/2305.00633/) (2023)
- [Rethinking with Retrieval: Faithful Large Language Model Inference](https://mlsanity.com/paper/2301.00303/) (2022)
- [ChemLLM: A Chemical Large Language Model](https://mlsanity.com/paper/2402.06852/) (2024)
- [CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models](https://mlsanity.com/paper/2305.14318/) (2023)
- [Improving Code Generation by Training with Natural Language Feedback](https://mlsanity.com/paper/2303.16749/) (2023)
- [Keeping it Simple: Language Models can learn Complex Molecular Distributions](https://mlsanity.com/paper/2112.03041/) (2021)
- [Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld](https://mlsanity.com/paper/2311.16714/) (2023)
- [A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2311.07954/) (2023)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning](https://mlsanity.com/paper/2402.12692/) (2024)

## Built on by (most cited first, 8 of 8)

- [UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models](https://mlsanity.com/paper/2502.00334/) (2025)
- [Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning](https://mlsanity.com/paper/2504.01911/) (2025)
- [InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning](https://mlsanity.com/paper/2509.12263/) (2025)
- [Mastering Olympiad-Level Physics with Artificial Intelligence](https://mlsanity.com/paper/2511.10515/) (2025)
- [Fine-Tuning Small Reasoning Models for Quantum Field Theory](https://mlsanity.com/paper/2604.18936/) (2026)
- [Decoupled Physical Modeling and Execution for Physics Reasoning](https://mlsanity.com/paper/2608.22126/) (2026)
- [Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models](https://mlsanity.com/paper/2607.05199/) (2026)
- [A Benchmark for LLM's Understanding of Middle School and High School Science Topics](https://mlsanity.com/paper/2609.32020/) (2026)

## Abstract (arXiv)

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%.