# Automated Transpilation of Imperative to Functional Code using Neural-Guided Program Synthesis (Extended Version)

arXiv: https://arxiv.org/abs/2203.09452 · HTML: https://mlsanity.com/paper/2203.09452/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2022.

## Built on by (most cited first, 7 of 7)

- [Multilingual Code Co-Evolution Using Large Language Models](https://mlsanity.com/paper/2307.14991/) (2023)
- [LLM-Aided Compilation for Tensor Accelerators](https://mlsanity.com/paper/2408.03408/) (2024)
- [Leveraging Artificial Intelligence on Binary Code Comprehension](https://mlsanity.com/paper/2210.05103/) (2022)
- [TorchQL: A Programming Framework for Integrity Constraints in Machine Learning](https://mlsanity.com/paper/2308.06686/) (2023)
- [Out of style: Misadventures with LLMs and code style transfer](https://mlsanity.com/paper/2406.10320/) (2024)
- [CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora](https://mlsanity.com/paper/2604.18027/) (2026)
- [SoK: Understanding (New) Security Issues Across AI4Code Use Cases](https://mlsanity.com/paper/2512.18456/) (2025)

## Abstract (arXiv)

While many mainstream languages such as Java, Python, and C# increasingly incorporate functional APIs to simplify programming and improve parallelization/performance, there are no effective techniques that can be used to automatically translate existing imperative code to functional variants using these APIs. Motivated by this problem, this paper presents a transpilation approach based on inductive program synthesis for modernizing existing code. Our method is based on the observation that the overwhelming majority of source/target programs in this setting satisfy an assumption that we call trace-compatibility: not only do the programs share syntactically identical low-level expressions, but these expressions also take the same values in corresponding execution traces. Our method leverages this observation to design a new neural-guided synthesis algorithm that (1) uses a novel neural architecture called cognate grammar network (CGN) and (2) leverages a form of concolic execution to prune partial programs based on intermediate values that arise during a computation. We have implemented our approach in a tool called NGST2 and use it to translate imperative Java and Python code to functional variants that use the Stream and functools APIs respectively. Our experiments show that NGST2 significantly outperforms several baselines and that our proposed neural architecture and pruning techniques are vital for achieving good results.