# Don't Transform the Code, Code the Transforms: Towards Precise Code Rewriting using LLMs

arXiv: https://arxiv.org/abs/2410.08806 · HTML: https://mlsanity.com/paper/2410.08806/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 12 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Learning Performance-Improving Code Edits](https://mlsanity.com/paper/2302.07867/) (2023)
- [Meta Large Language Model Compiler: Foundation Models of Compiler Optimization](https://mlsanity.com/paper/2407.02524/) (2024)
- [SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly](https://mlsanity.com/paper/2305.12520/) (2023)
- [Supersonic: Learning to Generate Source Code Optimizations in C/C++](https://mlsanity.com/paper/2309.14846/) (2023)

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

- [AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?](https://mlsanity.com/paper/2507.15887/) (2025)
- [VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations](https://mlsanity.com/paper/2503.19449/) (2025)
- [EditLord: Learning Code Transformation Rules for Code Editing](https://mlsanity.com/paper/2504.15284/) (2025)
- [Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking](https://mlsanity.com/paper/2508.19558/) (2025)
- [Generating High-Quality Datasets for Code Editing via Open-Source Language Models](https://mlsanity.com/paper/2509.25203/) (2025)
- [The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers](https://mlsanity.com/paper/2601.02045/) (2026)
- [Leveraging LLMs for Grammar Adaptation: A Study on Metamodel-Grammar Co-Evolution](https://mlsanity.com/paper/2605.21465/) (2026)
- [Agentic Generation of AST Transformation Rules for Fixing Breaking Updates](https://mlsanity.com/paper/2606.24446/) (2026)

## Abstract (arXiv)

Tools for rewriting, refactoring and optimizing code should be fast and correct. Large language models (LLMs), by their nature, possess neither of these qualities. Yet, there remains tremendous opportunity in using LLMs to improve code. We explore the use of LLMs not to transform code, but to code transforms. We propose a chain-of-thought approach to synthesizing code transformations from a small number of input/output code examples that incorporates execution and feedback. Unlike the direct rewrite approach, LLM-generated transformations are easy to inspect, debug, and validate. The logic of the rewrite is explicitly coded and easy to adapt. The compute required to run code transformations is minute compared to that of LLM rewriting. We test our approach on 16 Python code transformations and find that LLM- generated transforms are perfectly precise for 7 of them and less imprecise than direct LLM rewriting on the others. We hope to encourage further research to improving the precision of LLM code rewriting.