Software Refactoring Research with Large Language Models: A Systematic Literature Review
- Published
- Source
- arXiv
- Paper number
- 1453
- Field
- Software Engineering
- arXiv ID
- 2611.14027
Key points
- The authors reviewed 50 primary studies that use generative LLMs for refactoring.
- Java was the most-used language, and datasets were collected from open-source projects on GitHub, Apache, and F-Droid.
- One-Shot, Few-Shot, context-specific, and Chain-of-Thought prompting were most effective depending on the language; UTRefactor with Chain-of-Thought reduced test smells from 2,375 to 265, an 89% elimination.
- The definition of accuracy varies significantly across the literature, calling for a standardized measurement.
- The most often mentioned code smells were Large Class and Long Method, and the most often applied refactoring type was Extract Method.
Paper links
External research summaries. These are not HDATF publications or measured product results.