迈向数据系统的人工智能软件工厂
Towards an AI Software Factory for Data Systems
浏览论文内容
中文总结 AI 辅助
本文提出AI软件工厂加速数据系统全生命周期开发，在微软数十个代码库中实现3倍工程效率和22倍令牌效率提升，并指出开放性挑战。
中文摘要 AI 辅助
AI辅助编码工具在编码环节带来了显著的加速，但在端到端软件开发生命周期（SDLC）中的影响有限——这是阿姆达尔定律效应！本文讨论了我们在构建AI软件工厂方面的进展，该工厂加速了SDLC的所有阶段：目标设定、编码、审查和运维。AI软件工厂产生元数据流，通过微调模型权重和更新我们的世界模型（一个丰富的数据基底）实现自我改进。我们聚焦于数据系统和重要的进化式编码任务类别（即具有可测量的目标以进行爬山优化的任务），并报告了：1）在微软的大规模部署（数十个代码库）带来了相比智能体编码3倍的工程效率提升和高达22倍的令牌效率提升；2）若干开放性挑战。
英文摘要
AI-assisted coding tools deliver significant acceleration of coding, but only limited impact across the end-to-end software development lifecycle (SDLC)--an Amdahl's law effect! In this paper, we discuss our progress towards building an AI SW Factory that accelerates all the stages of SDLC-Targeting, Coding, Reviewing, and Ops. The AI SW Factory produces a metadata exhaust that enables self-improvement by fine-tuning model weights and updating our World Model (a rich data substrate). We focus on Data Systems and the important class of Evolutionary Coding Tasks (i.e., those with a measurable objective to hill-climb) and report on 1) scaled deployments at Microsoft (tens of repositories) leading to 3x engineering efficiency above agentic coding and up to 22x token efficiency, and 2) several open challenges.
发表机构
- Microsoft（微软）
- University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
机构由 AI 辅助整理，请以论文原文为准。
