发表机构
Linköping University（林雪平大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出将LLM驱动的代码重构作为软件维护的持续环节，围绕五个维度构建路线图，明确跨领域关注点，以推动自主重构向系统级质量维护发展。
AI 中文摘要
大型语言模型（LLM）在代码重构方面展现出良好的能力，但现有方法仍局限于方法级任务。本文提出将基于LLM的重构视为软件维护的持续组成部分，而非仅用于偶尔手动重构的工具。在这一构想下，AI智能体会持续监控、评估并改进代码库，以适配明确且不断发展的软件质量标准。本文围绕五个维度构建路线图：多目标优化问题、质量定义与评估、异构信号的多时间尺度整合、架构与设计模式、自主重构的信任机制；还确定了整合到持续交付流水线及成本考量为跨领域关注点。针对每个维度，本文分析了潜在挑战并提出开放性研究问题，这些维度构成了推进自主重构从孤立代码改进向系统级质量维护发展的研究议程。
英文摘要
Large language models have shown promising capabilities in code refactoring, but existing approaches remain limited to method-level tasks. In this paper, we envision LLM-based refactoring as a continuous component of software maintenance rather than a tool invoked only for occasional manual refactoring. Under this vision, AI agents continuously monitor, evaluate, and improve codebases against explicit and evolving notions of software quality. We present a roadmap organized around five dimensions: the multi-objective optimization problem, quality definition and evaluation, multi-timescale integration of heterogeneous signals, architecture and design pattern, and trust in autonomous refactoring. We further identify integration into continuous delivery pipelines and cost considerations as cross-cutting concerns. For each dimension, we analyze the underlying challenges and pose open research questions. These dimensions define a research agenda for advancing autonomous refactoring from isolated code improvements to system-level quality maintenance.
CommentsThe paper was accepted in ICSME 2026 in the Visions and Emerging Results Track
