arXiv：cs.LG· Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening, Reyhaneh Jabbarvand·· 3 小时前
ReCodeAgent：面向大规模代码仓库的语言无关翻译与验证多智能体工作流
ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
AI 导读
ReCodeAgent 是一种自主多智能体方法，可实现语言无关的仓库级代码翻译与验证，用户只需提供源语言项目和目标语言即可自动完成全仓库翻译与验证。在覆盖 6 种编程语言、4 种语言对的 118 个真实项目上，其测试通过率较此前技术提升 60.8%，平均成本 $15.3。研究还表明，相比单智能体架构，多智能体设计使测试通过率平均高出 40.4%。
正文
Abstract:Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs. Programming agents can enable PL-agnosticism in repository-level code translation and validation: they can synthesize code across many PLs and autonomously use existing tools specific to each PL's analysis. However, state-of-the-art has yet to offer a fully autonomous agentic approach for repository-level code translation and validation of large-scale programs. This paper proposes ReCodeAgent, an autonomous multi-agent approach for language-agnostic repository-level code translation and validation. Users only need to provide the project in the source PL and specify the target PL for ReCodeAgent to automatically translate and validate the entire repository. ReCodeAgent is the first technique to achieve high translation success rates across many PLs. We compare the effectiveness of ReCodeAgent with four alternative neuro-symbolic and agentic approaches to translate 118 real-world projects, with 1,975 LoC and 43 translation units for each project, on average. The projects cover 6 PLs and 4 PL pairs. Our results demonstrate that ReCodeAgent consistently outperforms prior techniques on translation correctness, improving test pass rate by 60.8% on ground-truth tests, with an average cost of $15.3. We also perform process-centric analysis of ReCodeAgent trajectories to confirm its procedural efficiency. Finally, we investigate how the design choices (a multi-agent vs. single-agent architecture) influence ReCodeAgent performance: on average, the test pass rate drops by 40.4%, and trajectories become 28% longer and persistently inefficient.
| Comments: | Published in ASE 2026 |
| Subjects: | Software Engineering (cs.SE); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.07341 [cs.SE] |
| (or arXiv:2604.07341v4 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2604.07341 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3832783.3837486
DOI(s) linking to related resources |
Submission history
From: Ali Reza Ibrahimzada [view email]
[v1]
Wed, 8 Apr 2026 17:54:08 UTC (395 KB)
[v2]
Wed, 5 Aug 2026 04:26:04 UTC (409 KB)
[v3]
Wed, 12 Aug 2026 17:33:31 UTC (420 KB)
[v4]
Thu, 8 Oct 2026 17:23:50 UTC (420 KB)
来源：arXiv：cs.LG · arxiv.org