BabelCoder: Agentic Code Translation with Specification Alignment

BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%. It comes from a paper posted to arXiv on 28 September 2026. 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.

Why it counts

BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%. We evaluate BabelCoder on four benchmark datasets and compare it against four state-of-the-art baselines. Prior work has explored translation and repair mechanisms, but lacks a structured, agentic framework where multiple specialized agents collaboratively improve translation quality.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.