Advancing Automated In-Isolation Validation in Repository-Level Code Translation

TL;DR

This paper introduces TRAM, a novel approach for repository-level code translation that combines context-aware type resolution with mock-based in-isolation validation, significantly improving translation quality and validation efficiency.

Contribution

TRAM integrates RAG-based type resolution with mock-based validation to enable high-quality, in-isolation repository-level code translation, reducing manual effort and validation costs.

Findings

Achieves state-of-the-art Java-to-Python translation performance.

Effectively resolves type mappings using contextual information and LLMs.

Enables validation of code fragments in isolation without heavy manual effort.

Abstract

Repository-level code translation aims to migrate entire repositories across programming languages while preserving functionality automatically. Despite advancements in repository-level code translation, validating the translations remains challenging. This paper proposes TRAM, which combines context-aware type resolution with mock-based in-isolation validation to achieve high-quality translations between programming languages. Prior to translation, TRAM retrieves API documentation and contextual code information for each variable type in the source language. It then prompts a large language model (LLM) with retrieved contextual information to resolve type mappings across languages with precise semantic interpretations. Using the automatically constructed type mapping, TRAM employs a custom serialization/deserialization workflow that automatically constructs equivalent mock objects in the target language. This enables each method fragment to be validated in isolation, without the high cost of using agents for translation validation, or the heavy manual effort required by existing approaches that rely on language interoperability. TRAM demonstrates state-of-the-art performance in Java-to-Python translation, underscoring the effectiveness of its integration of RAG-based type resolution with reliable in-isolation validation.