# Refactoring Codebases through Library Design

arXiv: https://arxiv.org/abs/2506.11058 · HTML: https://mlsanity.com/paper/2506.11058/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 13 of 13)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [Commit0: Library Generation from Scratch](https://mlsanity.com/paper/2412.01769/) (2024)
- [LILO: Learning Interpretable Libraries by Compressing and Documenting Code](https://mlsanity.com/paper/2310.19791/) (2023)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [ReGAL: Refactoring Programs to Discover Generalizable Abstractions](https://mlsanity.com/paper/2401.16467/) (2024)
- [RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code](https://mlsanity.com/paper/2503.07832/) (2025)
- [ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?](https://mlsanity.com/paper/2407.14044/) (2024)
- [babble: Learning Better Abstractions with E-Graphs and Anti-Unification](https://mlsanity.com/paper/2212.04596/) (2022)

## Built on by (most cited first, 4 of 4)

- [Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement](https://mlsanity.com/paper/2511.05931/) (2025)
- [CodeTaste: Can LLMs Generate Human-Level Code Refactorings?](https://mlsanity.com/paper/2603.04177/) (2026)
- [Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?](https://mlsanity.com/paper/2607.15439/) (2026)
- [Can Agents Design Libraries for Agents?](https://mlsanity.com/paper/2609.36730/) (2026)

## Abstract (arXiv)

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.