arXiv cs.AI· Mario Corchero, David Williams, Laszlo Kiss Kollar, Haowen Liu, Shivam Bairoliya, Gala Malbasic, Serkan Kirbas, Federica Sarro·· 3 小时前精选AI 评分64
Bloomberg 论文总结企业级 LLM 混合确定性代码迁移流水线经验
Hybrid LLM-Deterministic Pipelines for Enterprise-Scale Code Migration at Bloomberg
AI 导读
Bloomberg 团队在 arXiv 论文 arXiv:2611.05457 中报告跨数千个代码库的 LLM 辅助迁移实践，涵盖约 1,900 个 Python 打包仓库和约 6,700 个 C++ 构建系统仓库，共产生 2,333 个 PR、完成 729 次成功迁移。
推荐理由
来自 Bloomberg 的工业级实践报告，给出混合 LLM 与确定性架构的可迁移模式，并指出审查部署才是迁移瓶颈。
正文 · 原文
Abstract:Large organizations carry a long tail of infrastructure migrations that are worth doing but rarely urgent enough to compete with feature work, because each one costs significant engineering time per repository. This paper reports on our industrial experience from Automated Uplift, a multi-month initiative applying LLM-assisted migration pipelines across thousands of Bloomberg repositories. We examine two distinct production campaigns: a heterogeneous Python packaging migration (approx. 1,900 candidate repositories) and a uniform C++ build system migration (approx. 6,700 candidate repositories). Together, these campaigns generated 2,333 pull requests, resulting in 729 successful migrations. We detail our hybrid architectural solution which maximizes deterministic processing, confines the LLM to bounded file transformations within a pre-computed context, and incorporates runtime production telemetry (such as execution logs and usage traces). Our findings show that generating migrations turned out to be the easier part; the bottleneck was the cost, for owning teams, of reviewing, testing, and deploying them. These costs were lowered when changes could be verified directly in the pipeline before opening a PR (as with C++ compilation and test validation), and when the population was uniform enough for fixes to carry over from one repository to the next. We conclude by distilling our experience and findings into actionable, transferable patterns for architecting hybrid LLM-deterministic pipelines and scaling code migrations across the enterprise
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05457 [cs.SE] |
| (or arXiv:2611.05457v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05457 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Federica Sarro Professor [view email]
[v1]
Tue, 3 Nov 2026 18:55:28 UTC (96 KB)
来源：arXiv cs.AI · arxiv.org