# "Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution

arXiv: https://arxiv.org/abs/2605.22526 · HTML: https://mlsanity.com/paper/2605.22526/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios](https://mlsanity.com/paper/2410.12468/) (2024)
- [Agentic Refactoring: An Empirical Study of AI Coding Agents](https://mlsanity.com/paper/2511.04824/) (2025)
- [Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study](https://mlsanity.com/paper/2506.08311/) (2025)
- [Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios](https://mlsanity.com/paper/2503.12374/) (2025)
- [A Fine-grained Data Set and Analysis of Tangling in Bug Fixing Commits](https://mlsanity.com/paper/2011.06244/) (2020)
- [Untangling Fine-Grained Code Changes](https://mlsanity.com/paper/1502.06757/) (2015)
- [REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement](https://mlsanity.com/paper/2510.03588/) (2025)
- [On the Relationship between Refactoring Actions and Bugs: A Differentiated Replication](https://mlsanity.com/paper/2009.11685/) (2020)
- [How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench](https://mlsanity.com/paper/2507.02976/) (2025)
- [Bug Priority Change: An Empirical Study on Apache Projects](https://mlsanity.com/paper/2403.05059/) (2024)
- [A Survey of Reinforcement Learning for Software Engineering](https://mlsanity.com/paper/2507.12483/) (2025)
- [How do Agents Refactor: An Empirical Study](https://mlsanity.com/paper/2601.20160/) (2026)
- [Refactoring neq Bug-Inducing: Improving Defect Prediction with Code Change Tactics Analysis](https://mlsanity.com/paper/2507.19714/) (2025)

## Built on by (most cited first, 1 of 1)

- [Runnable Commit Untangling for Coding Agents](https://mlsanity.com/paper/2610.11593/) (2026)

## Abstract (arXiv)

Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which human developers naturally incorporate refactoring as part of the resolution process, resulting in tangled refactoring. Since LLMs are trained on large-scale open-source repositories, coding agents may inherit such behaviors. In this paper, we conduct an empirical study on Multi-SWE-bench, analyzing 3,691 valid patches generated by three agent frameworks with 12 LLMs. We find that coding agents introduce tangled refactorings less frequently (21.43% vs. 36.72%) and with lower intensity (0.66 vs. 1.75) than human developers, although they exhibit a broader diversity of refactoring types. Logistic regression analysis further shows that tangled refactorings are strongly associated with reduced compilability, while exhibiting no significant association with functional correctness. Based on these findings, we propose a refactoring-aware refinement approach that assesses the necessity and safety of tangled refactorings and selectively removes or repairs problematic operations. Our approach improves compilability from 19.34% to 38.33%, and additionally resolves 2.79% previously unresolved issues. Overall, this work presents the first step towards understanding tangled refactoring practices in agentic issue resolution and opens up avenues for future work.