用自演化框架让代码自动改进，零回归且持续变好
The Kitchen Loop: User-Spec-Driven Development for a Self-Evolving Codebase
- 用大模型模拟万倍人类速度测试代码规范
- 285轮迭代中1094个提交无一次回归
- 适合追求自动化演进的工程团队
代码生产已成常态，瓶颈在于知道该建什么以及证明其有效。我们提出厨房循环（Kitchen Loop）框架，基于统一信任模型实现自主、自我演化的软件系统：(1) 规范表面，列出产品声称支持的功能；(2) ‘作为用户x1000’，由大模型代理以1000倍人类频率模拟真实使用；(3) 无法伪造的真值验证测试；(4) 持续质量监控与自动暂停机制。在两个生产系统上验证，历经285+次迭代，生成1,094+个合并的Pull Request，回归检测器未发现任何回归（方法见第6.1节）。观察到规模化下的涌现特性：多轮自我纠错链、自主基础设施修复、质量门禁持续提升。这些组件并非首创；我们的贡献在于将其组合成经生产验证的系统，并建立使长期自主演进安全运行的操作规范。
原文摘要 · Abstract (English)
Code production is now a commodity; the bottleneck is knowing what to build and proving it works. We present the Kitchen Loop, a framework for autonomous, self-evolving software built on a unified trust model: (1) a specification surface enumerating what the product claims to support; (2) 'As a User x 1000', where an LLM agent exercises that surface as a synthetic power user at 1,000x human cadence; (3) Unbeatable Tests, ground-truth verification the code author cannot fake; and (4) Drift Control, continuous quality measurement with automated pause gates. We validate across two production systems over 285+ iterations, producing 1,094+ merged pull requests with zero regressions detected by the regression oracle (methodology in Section 6.1). We observe emergent properties at scale: multi-iteration self-correction chains, autonomous infrastructure healing, and monotonically improving quality gates. The primitives are not new; our contribution is their composition into a production-tested system with the operational discipline that makes long-running autonomous evolution safe.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。