BabelCoder: Agentic Code Translation with Specification Alignment

• URL: http://arxiv.org/abs/2512.06902v1
• Date: Sun, 07 Dec 2025 15:57:54 GMT
• Title: BabelCoder: Agentic Code Translation with Specification Alignment
• Abstract summary: We introduce BabelCoder, an agentic framework that performs code translation by decomposing the task into specialized agents for translation, testing, and refinement.<n>BabelCoder outperforms existing methods by 0.5%-13.5% in 94% of cases, achieving an average accuracy of 94.16%.
• Score: 7.64108921132755
• License: http://creativecommons.org/licenses/by/4.0/
• 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%.

Related papers

• Terminal-Bench-LILT: Multilingual Agentic Coding Benchmark Grounded in Language, Region, and Culture [3.8631030419868657]
  Terminal-Bench-LILT is a suite of 300 authentic coding tasks in ten languages.<n>Each task targets issues specific to non-English software development.<n> Evaluation of six frontier models reveals that even the strongest model reaches only 63.1% pass rate.
  arXiv  Detail & Related papers  (2026-08-11T14:05:47Z)
• GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation [2.845609289542755]
  Agent benchmarks remain largely English-centric, while their multilingual versions are often built with machine translation (MT) and limited post-editing.<n>We argue that, for agentic tasks, this minimal workflow can easily break benchmark validity through query-answer misalignment or culturally off-target context.<n>We propose a refined workflow for adapting English benchmarks into multiple languages with explicit functional alignment, cultural alignment, and difficulty calibration using both automated checks and human review.
  arXiv  Detail & Related papers  (2026-04-27T19:11:21Z)
• ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories [5.72515320527179]
  ReCodeAgent is an autonomous multi-agent approach for language-agnostic repository-level code translation and validation.<n>We compare the effectiveness of ReCodeAgent with four alternative neuro-symbolic and agentic approaches to translate 118 real-world projects.
  arXiv  Detail & Related papers  (2026-04-08T17:54:08Z)
• LegacyTranslate: LLM-based Multi-Agent Method for Legacy Code Translation [6.639896614747016]
  LegacyTranslate is a multi-agent framework for API-aware code translation.<n>Initial Translation Agent produces an initial Java translation using retrieved in-context examples.<n> API Grounding Agent aligns the code with existing APIs by retrieving relevant entries from an API knowledge base.<n> Refinement Agent iteratively refines the output using compiler feedback and API suggestions to improve correctness.
  arXiv  Detail & Related papers  (2026-03-14T17:51:07Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• VisCoder2: Building Multi-Language Visualization Coding Agents [63.63232038173407]
  We introduce three complementary resources for advancing visualization coding agents.<n>VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models.
  arXiv  Detail & Related papers  (2025-10-24T18:03:57Z)
• Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation [8.896718697354187]
  XL-CoGen produces high-quality code across multiple programming languages.<n>It integrates intermediate representation, code generation, translation, and automated repair.
  arXiv  Detail & Related papers  (2025-09-24T09:18:08Z)
• Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation [4.563830993050022]
  We introduce Ticket-Bench, a benchmark for multilingual agent evaluation in task-oriented scenarios.<n>Ticket-Bench simulates the domain of soccer ticket purchases across six major languages: Portuguese, English, Spanish, German, Italian, and French.<n>We evaluate a wide range of commercial and open-source LLMs, measuring function-calling accuracy and consistency across languages.
  arXiv  Detail & Related papers  (2025-09-17T23:13:47Z)
• Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraph [1.4582633500696451]
  The proposed system integrates three core components LangGraph, GLM4 Flash, and ChromaDB within a four step iterative workflow to deliver robust performance and functionality seamless.<n>LangGraph serves as a graph-based library for orchestrating tasks, providing precise control and execution while maintaining a unified state object for dynamic updates and consistency.<n>GLM4 Flash, a large language model, leverages its advanced capabilities in natural language understanding, contextual reasoning, and multilingual support to generate accurate code snippets based on user prompts.
  arXiv  Detail & Related papers  (2025-01-29T12:01:00Z)
• Supporting Cross-language Cross-project Bug Localization Using Pre-trained Language Models [2.5121668584771837]
  Existing techniques often struggle with generalizability and deployment due to their reliance on application-specific data. This paper proposes a novel pre-trained language model (PLM) based technique for bug localization that transcends project and language boundaries.
  arXiv  Detail & Related papers  (2024-07-03T01:09:36Z)
• AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection [69.79627042058048]
  AdaCCD is a novel cross-lingual adaptation method that can detect cloned codes in a new language without annotations in that language. We evaluate the cross-lingual adaptation results of AdaCCD by constructing a multilingual code clone detection benchmark consisting of 5 programming languages.
  arXiv  Detail & Related papers  (2023-11-13T12:20:48Z)
• Data Augmentation for Code Translation with Comparable Corpora and Multiple References [21.754147577489764]
  We build and analyze multiple types of comparable corpora, including programs generated from natural language documentation. To reduce overfitting to a single reference translation, we automatically generate additional translation references for available parallel data. Experiments show that our data augmentation techniques significantly improve CodeT5 for translation between Java, Python, and C++ by an average of 7.5% Computational Accuracy.
  arXiv  Detail & Related papers  (2023-11-01T06:01:22Z)
• CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model [58.127534002232096]
  This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset.
  arXiv  Detail & Related papers  (2023-10-10T02:38:44Z)
• CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation [8.979765541978292]
  CodeTransOcean is a large-scale comprehensive dataset that supports the largest variety of programming languages for code translation. CodeTransOcean consists of three novel multilingual datasets, namely, MultilingualTrans supporting translations between multiple popular programming languages, NicheTrans for translating between niche programming languages and popular ones, and LLMTrans for evaluating executability of translated code by large language models (LLMs)
  arXiv  Detail & Related papers  (2023-10-08T00:16:18Z)
• xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval [32.60391966381949]
  We introduce xCodeEval, the largest executable multilingual multitask benchmark to date. It features a total of $7$ tasks involving code understanding, generation, translation and retrieval. xCodeEval adopts an execution-based evaluation and offers a multilingual code execution engine, ExecEval.
  arXiv  Detail & Related papers  (2023-03-06T10:08:51Z)
• Zero-Shot Cross-lingual Semantic Parsing [56.95036511882921]
  We study cross-lingual semantic parsing as a zero-shot problem without parallel data for 7 test languages. We propose a multi-task encoder-decoder model to transfer parsing knowledge to additional languages using only English-Logical form paired data. Our system frames zero-shot parsing as a latent-space alignment problem and finds that pre-trained models can be improved to generate logical forms with minimal cross-lingual transfer penalty.
  arXiv  Detail & Related papers  (2021-04-15T16:08:43Z)
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP [68.2650714613869]
  We propose a data augmentation framework to generate multi-lingual code-switching data to fine-tune mBERT. Compared with the existing work, our method does not rely on bilingual sentences for training, and requires only one training process for multiple target languages.
  arXiv  Detail & Related papers  (2020-06-11T13:15:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.