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

• URL: http://arxiv.org/abs/2605.22526v1
• Date: Thu, 21 May 2026 14:18:29 GMT
• Title: "Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
• Abstract summary: We analyze 3,691 valid patches generated by three agent frameworks with 12 LLMs.<n>We find that coding agents introduce tangleds less frequently than human developers.<n>We propose a refinement approach that assesses the necessity and safety of tangleds and selectively removes problematic operations.
• Score: 12.987766332400213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• On the Influence of Refactoring Types on Merge Effort [70.15634443127651]
  We analyze 64 open-source Java projects and applied association rule mining to measure the strength of associations between specific types and merge effort.<n>Our results show that types relate to merge effort with varying strength.<n>Co-occurrences across parallel branches is associated with higher merge effort.
  arXiv  Detail & Related papers  (2026-08-15T19:28:01Z)
• RefactorAssist: Agentic Refinement for Reliable Code Refactoring [0.3657314044338856]
  Large Language Models (LLMs) have demonstrated potential for automating software engineering tasks.<n>LLMs often introduce subtle errors, leading to functional behavior changes and failed unit tests.<n>We develop the RefactorAssist agent to improve the functional correctness of LLM-generateds.
  arXiv  Detail & Related papers  (2026-08-02T01:32:22Z)
• SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks [55.76734816061826]
  We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints.<n>We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion.<n>No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%.
  arXiv  Detail & Related papers  (2026-03-25T19:26:44Z)
• SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring [20.694251041823097]
  Large Language Models (LLMs) have attracted wide interest for tackling software engineering tasks.<n>Existing benchmarks commonly suffer from three shortcomings.<n>SWE-Refactor comprises 1,099 developer-written, behavior-preserving LLMs mined from 18 Java projects.
  arXiv  Detail & Related papers  (2026-02-03T16:36:29Z)
• Agentic Refactoring: An Empirical Study of AI Coding Agents [9.698067623031909]
  Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are transforming the software engineering landscape.<n>These AI-powered systems function as autonomous teammates capable of planning and executing complex development tasks.<n>There is a critical lack of empirical understanding regarding how agentic is utilized in practice, how it compares to human-driven, and what impact it has on code quality.
  arXiv  Detail & Related papers  (2025-11-06T21:24:38Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Refactoring $\neq$ Bug-Inducing: Improving Defect Prediction with Code Change Tactics Analysis [54.361900378970134]
  Just-in-time defect prediction (JIT-DP) aims to predict the likelihood of code changes resulting in software defects at an early stage.<n>Prior research has largely ignored code during both the evaluation and methodology phases, despite its prevalence.<n>We propose Code chAnge Tactics (CAT) analysis to categorize code and its propagation, which improves labeling accuracy in the JIT-Defects4J dataset by 13.7%.
  arXiv  Detail & Related papers  (2025-07-25T23:29:25Z)
• Relating Complexity, Explicitness, Effectiveness of Refactorings and Non-Functional Requirements: A Replication Study [39.82126443893643]
  Self-affirmed (SAR) is where developers explicitly state their intent to simplify requirements.<n>This study expanded the scope of Soares et al.'s study by doubling the number of projects and a significantly larger set of validated instances.<n>We observed that when developers explicitly state their intent, the resulting changes typically involve a combination of different types, making them more complex.
  arXiv  Detail & Related papers  (2025-05-12T19:26:33Z)
• MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM Collaboration [44.75848695076576]
  We introduce MANTRA, a comprehensive Large Language Models agent-based framework.<n>ManTRA integrates Context-Aware Retrieval-Augmented Generation, coordinated Multi-Agent Collaboration, and Verbal Reinforcement Learning.<n> Experimental results demonstrate that MANTRA substantially surpasses a baseline LLM model.
  arXiv  Detail & Related papers  (2025-03-18T15:16:51Z)
• An Empirical Study on the Potential of LLMs in Automated Software Refactoring [9.157968996300417]
  We investigate the potential of large language models (LLMs) in automated software. We find that 13 out of the 176 solutions suggested by ChatGPT and 9 out of the 137 solutions suggested by Gemini were unsafe in that they either changed the functionality of the source code or introduced syntax errors.
  arXiv  Detail & Related papers  (2024-11-07T05:35:55Z)
• Do code refactorings influence the merge effort? [80.1936417993664]
  Multiple contributors frequently change the source code in parallel to implement new features, fix bugs, existing code, and make other changes. These simultaneous changes need to be merged into the same version of the source code. Studies show that 10 to 20 percent of all merge attempts result in conflicts, which require the manual developer's intervention to complete the process.
  arXiv  Detail & Related papers  (2023-05-10T13:24:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.