arXiv cs.AI· Farzad Habibi, Changrong Wu, Jinzhou Jiang, Guohan Lu·· 15 小时前AI 评分40
CodeMeepo：面向仓库级代码迁移与优化的多智能体工作流
CodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization
AI 导读
CodeMeepo 是一个用于大型仓库完整、高效迁移的多智能体流水线，在三种语言对的九个测试对象上均取得最佳通过率，比使用同一模型的 SOTA 多智能体基线多通过 18% 的测试。每个里程碑由智能体不参与编写或修改的固定外部 oracle 评估，并通过独立的 parity 评估把发现的差距重新纳入计划。其优化阶段在生产守护进程上改善了半数基准，平均提升 25%。
正文 · 原文
Abstract:Repository-level code migration rewrites an entire project in a new programming language while preserving its observable behavior. It is challenging because behavior spans interdependent modules, dependencies and build infrastructure must be adapted to the target ecosystem, and the source code is often the only specification.
Large language model agents can now attempt these migrations end to end, but three challenges remain. First, an agent that writes both the translation and its acceptance tests may overlook the same requirements in both, leaving missing or incorrect behavior undetected. Second, large repositories can exceed a model's context window, and dividing the work into smaller tasks does not ensure that all required behavior is migrated. Third, even behaviorally correct translations may be slower than the original implementation.
We present CodeMeepo, a multi-agent pipeline for complete and efficient migration of large repositories. Each milestone is evaluated against a fixed external oracle that the agents neither author nor modify. A separate parity assessment compares source and target components in scope and adds identified gaps back into the plan as required work. Ordered milestones limit the scope of each task, while cumulative regression checks guard against breaking already-migrated behavior. A benchmark-guided optimization phase addresses performance, followed by full-suite conformance testing and repair. Eight specialized agent roles communicate through file artifacts, and a deterministic state machine governs repair, deferral, scope changes, and termination.
On nine subjects in three language pairs, CodeMeepo achieves the best pass rate on every subject and passes 18% more tests than a state-of-the-art multi-agent baseline using the same model. On a production daemon, its optimization phase improves half of the benchmarks, by 25% on average.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34633 [cs.SE] |
| (or arXiv:2610.34633v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34633 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Farzad Habibi [view email]
[v1]
Sun, 25 Oct 2026 23:15:38 UTC (151 KB)
来源：arXiv cs.AI · arxiv.org