综述：自进化编程智能体（Self-Evolving Coding Agents）

Computer Science > Software Engineering arXiv:2608.03392 (cs) [Submitted on 4 Aug 2026 (v1), last revised 24 Sep 2026 (this version, v4)] Title:Self-Evolving Coding Agents Authors:Hao Zhou, Haichuan Hu, Tianyu Luo, Ye Shang, Chunrong Fang, Zhenyu Chen, Liang Xiao, Quanjun Zhang View a PDF of the paper titled Self-Evolving Coding Agents, by Hao Zhou and 7 other authors View PDF HTML (experimental) Abstract:Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing coding agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and repair attempts leave reusable experience. This tension has motivated a growing body of work on self-evolving coding agents, where the agent improves its future behavior by persistently updating its framework, memory, skills and tools, components, workflow and topology, or environment and context from prior coding interactions. In this survey, we provide a structured synthesis of this emerging area. We first define the concept of self-evolving coding agents and distinguish it from conventional coding agents and general self-evolving agents. We then develop a taxonomy centered on the targets of evolution, complemented by two orthogonal perspectives: when evolution occurs and which code-specific signals drive it. We further examine the benchmarks used to measure the effect of evolution and related coding products. Across the literature, we find that executable feedback, repository-level context, and coding trajectories make software engineering a natural domain for agent self-evolution, but also introduce challenges in feedback reliability, benchmark overfitting, reversibility, system complexity, safety, cost, and generalization. By organizing existing work around these dimensions, this survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems. Subjects: Software Engineering (cs.SE) Cite as: arXiv:2608.03392 [cs.SE] (or arXiv:2608.03392v4 [cs.SE] for this version) https://doi.org/10.48550/arXiv.2608.03392 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Haichuan Hu [view email] [v1] Tue, 4 Aug 2026 09:43:46 UTC (489 KB) [v2] Thu, 20 Aug 2026 06:07:25 UTC (1,064 KB) [v3] Sat, 29 Aug 2026 04:09:28 UTC (1,081 KB) [v4] Thu, 24 Sep 2026 08:10:33 UTC (2,750 KB) Full-text links: Access Paper: View a PDF of the paper titled Self-Evolving Coding Agents, by Hao Zhou and 7 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.SE new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)