循环工程：构建模块、采用情况及影响
Loop Engineering: Building Blocks, Adoption, and Impact
浏览论文内容
中文总结 AI 辅助
本文对新兴循环工程领域开展探索性研究，分析其构建模块、开源项目采用情况，挖掘36710个仓库发现217个存在自主智能体循环，并规划了智能体自主层级的对照研究。
中文摘要 AI 辅助
在过去数月中，开发者引导智能体AI编码工具的方式已提升了数个抽象层级，从编写提示词发展到构建上下文，再到配置模型周边的管控机制。2026年6月，从业者开始描述一个名为循环工程（loop engineering）的新层级：开发者不再交互式地向智能体输入提示词，而是设计系统为其生成提示词。这些系统会按计划或仓库事件启动智能体运行，并在机器可核查的条件满足时停止运行。该术语迅速传播，伴随大胆断言与强烈质疑，但它在软件项目中的采用情况尚未被量化。本文对新兴灰色文献开展探索性综述，这些文献在精心设计的循环应包含的内容上基本达成共识：受触发的智能体运行、受机器可核查停止条件的约束、持久状态文件、验证器子智能体、令牌预算，以及明确的人类介入升级节点。基于该综述，本文推导了针对开源项目中循环工程的实证研究议程，分析了其中哪些方面可从仓库数据中追踪，并报告了对36710个软件仓库的探索性挖掘研究。在启发式匹配的256个仓库中，有217个被证实存在自主智能体循环的运行。这些仓库提交了循环周边的配置，但几乎没有一个提交文献所述的状态文件，且循环的运行时状态未被纳入版本控制。最后，本文概述了一项计划开展的、关于智能体自主层级及其对工作量与结果影响的对照研究。
英文摘要
Over the past months, the way developers direct agentic AI coding tools has moved up several levels of abstraction, from phrasing prompts to engineering context to configuring the harness around the model. In June 2026, practitioners began to describe a further level called loop engineering: Instead of prompting an agent interactively, developers design systems that prompt agents for them. These systems start agent runs on a schedule or on repository events and stop them when a machine-checkable condition holds. The term spread rapidly, accompanied by bold claims and vocal skepticism, but its adoption in software projects has not been measured. We present an exploratory review of the emerging gray literature, which largely agrees on what a well-engineered loop contains: triggered agent runs bounded by machine-checkable stop conditions, persistent state files, verifier sub-agents, token budgets, and defined points of escalation to humans. From this review, we derive a research agenda for the empirical study of loop engineering in open-source projects, analyze which of its aspects are traceable from repository data, and report an exploratory mining study of 36,710 software repositories. We confirmed the operation of autonomous agent loops in 217 of the 256 repositories our heuristics matched. The repositories commit the configuration around these loops, but almost none commits the state files the discourse prescribes, and the loops' runtime state remains outside version control. We conclude by outlining a planned controlled study of agent autonomy levels and their effect on effort and outcomes.
