ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories
2026-04-08 • Software Engineering
Software Engineering
AI summaryⓘ
The authors introduce ReCodeAgent, a system that automatically translates and checks entire code projects between different programming languages without needing users to adapt the tools for each language pair. They tested it on real projects across six programming languages and found it worked much better than previous methods, improving the success of correct translations by over 60%. Their analysis also showed that using multiple agents working together made the process more efficient and accurate than relying on a single agent. Overall, their work advances the ability to translate large codebases between languages with less manual effort.
code translationrepository-levelprogramming languagesautonomous agentsmulti-agent systemcode validationtest pass rateneuro-symbolic methodslarge-scale softwaresoftware engineering
Authors
Ali Reza Ibrahimzada, Brandon Paulsen, Daniel Kroening, Reyhaneh Jabbarvand
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 (C, Go, Java, JavaScript, Python, and Rust) and 4 PL pairs (C-Rust, Go-Rust, Java-Python, Python-JavaScript). 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.