RepoTransAgent: Multi-Agent LLM Framework for Repository-Aware Code Translation

TL;DR

RepoTransAgent is a multi-agent framework that improves repository-aware code translation by decomposing tasks, using retrieval-augmented generation, adaptive prompts, and error correction, significantly outperforming existing methods on Java-C# translation.

Contribution

It introduces a novel multi-agent framework that systematically decomposes code translation into specialized subtasks with retrieval, adaptive prompts, and error correction, enhancing accuracy and robustness.

Findings

Achieves up to 55.34% compile rate and 45.84% pass rate on Java-C# translation.

Outperforms state-of-the-art baselines in real-world repository scenarios.

Demonstrates robustness and generalizability across different LLMs.

Abstract

Repository-aware code translation is critical for modernizing legacy systems, enhancing maintainability, and enabling interoperability across diverse programming languages. While recent advances in large language models (LLMs) have improved code translation quality, existing approaches face significant challenges in practical scenarios: insufficient contextual understanding, inflexible prompt designs, and inadequate error correction mechanisms. These limitations severely hinder accurate and efficient translation of complex, real-world code repositories. To address these challenges, we propose RepoTransAgent, a novel multi-agent LLM framework for repository-aware code translation. RepoTransAgent systematically decomposes the translation process into specialized subtasks-context retrieval, dynamic prompt construction, and iterative code refinement-each handled by dedicated agents. Our approach leverages retrieval-augmented generation (RAG) for contextual information gathering, employs adaptive prompts tailored to varying repository scenarios, and introduces a reflection-based mechanism for systematic error correction. We evaluate RepoTransAgent on hundreds of Java-C# translation pairs from six popular open-source projects. Experimental results demonstrate that RepoTransAgent significantly outperforms state-of-the-art baselines in both compile and pass rates. Specifically, RepoTransAgent achieves up to 55.34% compile rate and 45.84% pass rate. Comprehensive analysis confirms the robustness and generalizability of RepoTransAgent across different LLMs, establishing its effectiveness for real-world repository-aware code translation.