Refactoring Codebases through Library Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908576560185344 |
|---|---|
| author | Kovacic, Ziga Chiu, Justin T. Lee, Celine Zhao, Wenting Ellis, Kevin |
| author_facet | Kovacic, Ziga Chiu, Justin T. Lee, Celine Zhao, Wenting Ellis, Kevin |
| contents | Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into reusable components. This challenge becomes particularly relevant as code agents become used to solve isolated one-off programming problems. We investigate code agents' capacity to refactor code in ways that support growth and reusability. We first investigate what makes a good refactoring, finding via simulation results and a human study that Minimum Description Length best correlates with preferable refactorings. We then present both a benchmark and a method for refactoring: MiniCode, a benchmark where multiple files must be refactored into a shared library, and Librarian, a sample-and-rerank method for generating reusable libraries. We compare Librarian to state-of-the-art library generation methods, and study it on real-world code bases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11058 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Refactoring Codebases through Library Design Kovacic, Ziga Chiu, Justin T. Lee, Celine Zhao, Wenting Ellis, Kevin Software Engineering Artificial Intelligence Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into reusable components. This challenge becomes particularly relevant as code agents become used to solve isolated one-off programming problems. We investigate code agents' capacity to refactor code in ways that support growth and reusability. We first investigate what makes a good refactoring, finding via simulation results and a human study that Minimum Description Length best correlates with preferable refactorings. We then present both a benchmark and a method for refactoring: MiniCode, a benchmark where multiple files must be refactored into a shared library, and Librarian, a sample-and-rerank method for generating reusable libraries. We compare Librarian to state-of-the-art library generation methods, and study it on real-world code bases. |
| title | Refactoring Codebases through Library Design |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2506.11058 |