# AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation

arXiv: https://arxiv.org/abs/2410.24117 · HTML: https://mlsanity.com/paper/2410.24117/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 56 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [Tree-to-tree Neural Networks for Program Translation](https://mlsanity.com/paper/1802.03691/) (2018)
- [Leveraging Automated Unit Tests for Unsupervised Code Translation](https://mlsanity.com/paper/2110.06773/) (2021)
- [AVATAR: A Parallel Corpus for Java-Python Program Translation](https://mlsanity.com/paper/2108.11590/) (2021)
- [CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation](https://mlsanity.com/paper/2310.04951/) (2023)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [StructCoder: Structure-Aware Transformer for Code Generation](https://mlsanity.com/paper/2206.05239/) (2022)
- [On the Evaluation of Neural Code Translation: Taxonomy and Benchmark](https://mlsanity.com/paper/2308.08961/) (2023)
- [VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners](https://mlsanity.com/paper/2404.18852/) (2024)
- [Rectifier: Code Translation with Corrector via LLMs](https://mlsanity.com/paper/2407.07472/) (2024)
- [CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model](https://mlsanity.com/paper/2310.06266/) (2023)
- [Program Decomposition and Translation with Static Analysis](https://mlsanity.com/paper/2401.12412/) (2024)

## Built on by (most cited first, 28 of 28)

- [EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checking](https://mlsanity.com/paper/2502.12466/) (2025)
- [RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation](https://mlsanity.com/paper/2412.17744/) (2024)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [EffiReasonTrans: RL-Optimized Reasoning for Code Translation](https://mlsanity.com/paper/2510.18863/) (2025)
- [SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?](https://mlsanity.com/paper/2608.23564/) (2026)
- [MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair](https://mlsanity.com/paper/2509.16187/) (2025)
- [Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement](https://mlsanity.com/paper/2503.22512/) (2025)
- [Project-Level C-to-Rust Translation via Pointer Knowledge Graphs](https://mlsanity.com/paper/2510.10956/) (2025)
- [Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings](https://mlsanity.com/paper/2512.14917/) (2025)
- [An Empirical Study of Reasoning Steps in Thinking Code LLMs](https://mlsanity.com/paper/2511.05874/) (2025)
- [ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories](https://mlsanity.com/paper/2604.07341/) (2026)
- [When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation](https://mlsanity.com/paper/2510.16809/) (2025)
- [BabelCoder: Agentic Code Translation with Specification Alignment](https://mlsanity.com/paper/2512.06902/) (2025)
- [ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation](https://mlsanity.com/paper/2603.25770/) (2026)
- [Q-Bridge: Code Translation for Quantum Machine Learning via LLMs](https://mlsanity.com/paper/2603.27836/) (2026)
- [ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust Transpilation](https://mlsanity.com/paper/2604.12048/) (2026)
- [CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora](https://mlsanity.com/paper/2604.18027/) (2026)
- [A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights](https://mlsanity.com/paper/2507.16037/) (2025)
- [Learning Bug Context for PyTorch-to-JAX Translation with LLMs](https://mlsanity.com/paper/2510.09898/) (2025)
- [The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers](https://mlsanity.com/paper/2601.02045/) (2026)
- [Revisiting the Role of Natural Language Code Comments in Code Translation](https://mlsanity.com/paper/2601.16661/) (2026)
- [Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation](https://mlsanity.com/paper/2606.17683/) (2026)
- [Entropy-based Code Adversarial Translation for Real-world Repository Migration](https://mlsanity.com/paper/2608.09273/) (2026)
- [Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT](https://mlsanity.com/paper/2608.13681/) (2026)
- [Identifying Latent Declarative Representations of Code for Assisting Repository Migration](https://mlsanity.com/paper/2608.23619/) (2026)
- [CoSTAR: Data Synthesis-Driven Constraint-Aware COBOL Section Summarization for Legacy System Modernization](https://mlsanity.com/paper/2609.11332/) (2026)
- [ORCA: Evaluating LLMs on Data Science Code Translation](https://mlsanity.com/paper/2609.30749/) (2026)

## Abstract (arXiv)

Code translation transforms programs from one programming language (PL) to another. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can become obsolete as the PLs evolve and cannot generalize to other PLs. Recent studies have explored the automation of code translation using Large Language Models (LLMs). One key observation is that such techniques may work well for crafted benchmarks but fail to generalize to the scale and complexity of real-world projects with dependencies, custom types, PL-specific features, etc. We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation. AlphaTrans translates both source and test code, and employs multiple levels of validation to ensure the translation preserves the functionality of the source program. To break down the problem for LLMs, AlphaTrans leverages program analysis to decompose the program into fragments and translates them in the reverse call order. We leveraged AlphaTrans to translate ten real-world open-source projects consisting of <836, 8575, 2719> classes, methods, and tests. AlphaTrans breaks down these projects into 17874 fragments and translates the entire repository. 96.40% of the translated fragments are syntactically correct, and AlphaTrans validates the translations' runtime behavior and functional correctness for 27.03% and 25.14% of fragments. On average, the integrated translation and validation take 34 hours to translate a project, showing its scalability in practice. For the incorrect translations, AlphaTrans generates a report including existing translation, stack trace, test errors, or assertion failures. We provided these artifacts to two developers to fix the translation bugs in four projects. They were able to fix the issues in 20.1 hours on average and achieve all passing tests.