BabelCoder: Agentic Code Translation with Specification Alignment

TL;DR

BabelCoder is an agentic framework for code translation that decomposes the task into specialized agents, leveraging structured collaboration to improve accuracy in multilingual code migration tasks.

Contribution

It introduces a novel agentic approach with specialized agents for translation, testing, and refinement, enhancing code translation accuracy over existing methods.

Findings

Outperforms baselines by 0.5%-13.5% in 94% of cases

Achieves an average accuracy of 94.16%

Effective across four benchmark datasets

Abstract

As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to another. While automatic code translation offers a promising solution, it has long remained a challenging task. Recent advancements in Large Language Models (LLMs) have shown potential for this task, yet existing approaches remain limited in accuracy and fail to effectively leverage contextual and structural cues within the code. Prior work has explored translation and repair mechanisms, but lacks a structured, agentic framework where multiple specialized agents collaboratively improve translation quality. In this work, we introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement, each responsible for a specific aspect such as generating code, validating correctness, or repairing errors. We evaluate BabelCoder on four benchmark datasets and compare it against four state-of-the-art baselines. BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%.