Code Translation

Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Python, with weaker performance in languages like Rust and OCaml. Since real-world systems are inherently polyglot, robust multilingual code intelligence is crucial. This survey focuses on two key tasks: multilingual code generation from shared natural-language requirements, and multilingual code translation that preserves semantics across languages. It reviews representative methods, benchmarks, and evaluation metrics, and highlights challenges and opportunities for trustworthy cross-language generalization.

Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream applications, from modernizing large legacy codebases to augmenting data for low-resource PLs. Recent large language model (LLM)-based approaches have demonstrated immense potential for code translation. Among these approaches, training-based methods are particularly important because LLMs currently do not effectively adapt to domain-specific settings that suffer from a lack of knowledge without targeted training. This limitation is evident in transpilation tasks involving low-resource PLs. However, existing training-based approaches rely on a pairwise transpilation paradigm, making it impractical to support a diverse range of PLs. This limitation is particularly prominent for low-resource PLs due to a scarcity of training data. Furthermore, these methods suffer from suboptimal reinforcement learning (RL) reward formulations. To address these limitations, we propose CodePivot, a training framework that leverages Python as an intermediate representation (IR), augmented by a novel RL reward mechanism, Aggressive-Partial-Functional reward, to bootstrap the model's multilingual transpilation ability without requiring parallel corpora. Experiments involving 10 PLs show that the resulting 7B model, trained on Python-to-Others tasks, consistently improves performance across both general and low-resource PL-related transpilation tasks. It outperforms substantially larger mainstream models with hundreds of billions more parameters, such as Deepseek-R1 and Qwen3-235B-A22B-Instruct-2507, on Python-to-Others tasks and Others-to-All tasks, respectively. In addition, it outperforms its counterpart trained directly on Any-to-Any tasks on general transpilation tasks. The code and data are available at https://github.com/lishangyu-hkust/CodePivot.

Automatic translation of natural language mathematics into faithful Lean 4 code is hindered by the fundamental dissonance between informal set-theoretic intuition and strict formal type theory. This gap often causes LLMs to hallucinate non-existent library definitions, resulting in code that fails to compile or lacks semantic fidelity. In this work, we investigate the effectiveness of tool-augmented agents for this task through a systematic factorial analysis of three distinct tool categories: Fine-tuned Model Querying (accessing expert drafts), Knowledge Search (retrieving symbol definitions), and Compiler Feedback (verifying code via a Lean REPL). We first benchmark the agent against one-shot baselines, demonstrating large gains in both compilation success and semantic equivalence. We then use the factorial decomposition to quantify the impact of each category, isolating the marginal contribution of each tool type to overall performance.

Cross-language migration of large software systems is a persistent engineering challenge, particularly when the source codebase evolves rapidly. We present a methodology for LLM-assisted continuous code translation in which a large language model translates a production Rust codebase (648K LOC, 65 crates) into Python (41K LOC, 28 modules), with public agent benchmarks as the objective function driving iterative refinement. Our subject system is Codex CLI, a production AI coding agent. We demonstrate that: (1) the Python port resolves 59/80 SWE-bench Verified tasks (73.8%) versus Rust's 56/80 (70.0%), and achieves 42.5% on Terminal-Bench versus Rust's 47.5%, confirming near-parity on real-world agentic tasks; (2) benchmark-driven debugging, revealing API protocol mismatches, environment pollution, a silent WebSocket failure mode, and an API 400 crash, is more effective than static testing alone; (3) the architecture supports continuous upstream synchronisation via an LLM-assisted diff-translate-test loop; and (4) the Python port has evolved into a capability superset with 30 feature-flagged extensions (multi-agent orchestration, semantic memory, guardian safety, cost tracking) absent from Rust, while preserving strict parity mode for comparison. Our evaluation shows that for LLM-based agents where API latency dominates, Python's expressiveness yields a 15.9x code reduction with negligible performance cost, while the benchmark-as-objective-function methodology provides a principled framework for growing a cross-language port from parity into an extended platform.

Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs. Programming agents can enable PL-agnosticism in repository-level code translation and validation: they can synthesize code across many PLs and autonomously use existing tools specific to each PL's analysis. However, state-of-the-art has yet to offer a fully autonomous agentic approach for repository-level code translation and validation of large-scale programs. This paper proposes ReCodeAgent, an autonomous multi-agent approach for language-agnostic repository-level code translation and validation. Users only need to provide the project in the source PL and specify the target PL for ReCodeAgent to automatically translate and validate the entire repository. ReCodeAgent is the first technique to achieve high translation success rates across many PLs. We compare the effectiveness of ReCodeAgent with four alternative neuro-symbolic and agentic approaches to translate 118 real-world projects, with 1,975 LoC and 43 translation units for each project, on average. The projects cover 6 PLs and 4 PL pairs. Our results demonstrate that ReCodeAgent consistently outperforms prior techniques on translation correctness, improving test pass rate by 60.8% on ground-truth tests, with an average cost of $15.3. We also perform process-centric analysis of ReCodeAgent trajectories to confirm its procedural efficiency. Finally, we investigate how the design choices (a multi-agent vs. single-agent architecture) influence ReCodeAgent performance: on average, the test pass rate drops by 40.4%, and trajectories become 28% longer and persistently inefficient.

We present Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation, a two-phase pipeline for translating real-world C projects to safe Rust. Existing approaches either produce unsafe output without memory-safety guarantees or translate functions in isolation, failing to detect cross-unit type mismatches or handle unsafe constructs requiring whole-program reasoning. Furthermore, function-level LLM pipelines require coordinated caller updates when type signatures change, while project-scale systems often fail to produce compilable output under real-world dependency complexity. Encrust addresses these limitations by decoupling boundary adaptation from function logic via an Application Binary Interface (ABI)-preserving wrapper pattern and validating each intermediate state against the integrated codebase. Phase 1 (Encapsulated Substitution) translates each function using an ABI-preserving wrapper that splits it into two components: a caller-transparent shim retaining the original raw-pointer signature, and a safe inner function targeted by the LLM with a clean, scope-limited prompt. This enables independent per-function type changes with automatic rollback on failure, without coordinated caller updates. A deterministic, type-directed wrapper elimination pass then removes wrappers after successful translation. Phase 2 (Agentic Refinement) resolves unsafe constructs beyond per-function scope, including static mut globals, skipped wrapper pairs, and failed translations, using an LLM agent operating on the whole codebase under a baseline-aware verification gate. We evaluate Encrust on 7 GNU Coreutils programs and 8 libraries from the Laertes benchmark, showing substantial unsafe-construct reduction across all 15 programs while maintaining full test-vector correctness.

Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness. While recent LLM-based approaches attempt to refine decompiled pseudocode, they typically either optimize solely for readability or rely on static analysis for evaluation. This makes them prone to "semantic hallucinations" that compromise accuracy and fail to resolve actual runtime failures. For critical tasks like software modernization and vulnerability remediation, recovered code must not only compile but replicate the original binary's behavior. We present PCodeTrans, a feedback-driven framework that bridges the gap between decompilation, recompilation, and rigorous function-level dynamic validation. After extracting a minimal yet coherent context to guarantee recompilability, PCodeTrans employs an in situ substitutable engine to hot-swap the compiled function directly into the unmodified binary, natively preserving its authentic execution context and global dependencies. Guided by fine-grained differential tracing, PCodeTrans generates precise runtime feedback to iteratively guide an LLM in repairing semantic discrepancies. Evaluated on Coreutils and Binutils, PCodeTrans achieves unprecedented recovery performance when rectifying raw Hex-Rays outputs, attaining 100% function-level compilability on unstripped binaries alongside 99.55% and 99.89% test-validated behavioral consistency, respectively. In doing so, it resolves 76.56% and 79.74% of logic errors exposed by official test suites. Exhibiting exceptional resilience, PCodeTrans maintains over 96% behavioral consistency even on fully stripped binaries. By significantly outperforming all existing baselines, PCodeTrans paves a practical path to reliably translate decompiled pseudocode into compilable and executable equivalents.

Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs), leaving general-purpose languages that suffer from data scarcity underexplored. To address this gap, we introduce CangjieBench, a contamination-free benchmark for Cangjie, a representative low-resource general-purpose language. The benchmark comprises 248 high-quality samples manually translated from HumanEval and ClassEval, covering both Text-to-Code and Code-to-Code tasks. We conduct a systematic evaluation of diverse LLMs under four settings: Direct Generation, Syntax-Constrained Generation, Retrieval-Augmented Generation (RAG), and Agent. Experiments reveal that Direct Generation performs poorly, whereas Syntax-Constrained Generation offers the best trade-off between accuracy and computational cost. Agent achieve state-of-the-art accuracy but incur high token consumption. Furthermore, we observe that Code-to-Code translation often underperforms Text-to-Code generation, suggesting a negative transfer phenomenon where models overfit to the source language patterns. We hope that our work will offer valuable insights into LLM generalization to unseen and low-resource programming languages. Our code and data are available at https://github.com/cjhCoder7/CangjieBench.

Large language models (LLMs) have shown strong performance on code translation between widely used programming languages. However, translation becomes much less reliable for domain-specific code, where correctness depends on framework-specific APIs and execution semantics. One example is translating deep-learning code from PyTorch to JAX, where LLM outputs often contain subtle bugs or non-idiomatic usage that prevents execution or changes behavior. Prior work suggests that curated bug-fix data from LLM-generated code can help improve code generation quality, but such resources are still limited for PyTorch-to-JAX translation. In this work, we introduce T2J, a benchmark of LLM translation bugs paired with developer-written fixes for PyTorch-to-JAX code. We start from 20 kernels in the TorchLeet dataset, translate them to JAX using the weak LLM gpt-4o-mini, and hire software developers to debug and repair the generated JAX implementations. We then use T2J to improve PyTorch-to-JAX translation for the weak LLM gpt-4o-mini via in-context learning. Our evaluation shows that using T2J yields up to 20% improvement of our proposed metric T2J-CodeTrans-Score.

Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators lack native Fortran bindings, creating an urgent need to modernize legacy codes for portability. Frameworks like Kokkos provide performance portability and a single-source C++ abstraction, but manual Fortran-to-Kokkos porting demands significant expertise and time. Large language models (LLMs) have shown promise in source-to-source code generation, yet their use in fully autonomous workflows for translating and optimizing parallel code remains largely unexplored, especially for performance portability across diverse hardware. This paper presents an agentic AI workflow where specialized LLM "agents" collaborate to translate, validate, compile, run, test, debug, and optimize Fortran kernels into portable Kokkos C++ programs. Results show the pipeline modernizes a range of benchmark kernels, producing performance-portable Kokkos codes across hardware partitions. Paid OpenAI models such as GPT-5 and o4-mini-high executed the workflow for only a few U.S. dollars, generating optimized codes that surpassed Fortran baselines, whereas open-source models like Llama4-Maverick often failed to yield functional codes. This work demonstrates the feasibility of agentic AI for Fortran-to-Kokkos transformation and offers a pathway for autonomously modernizing legacy scientific applications to run portably and efficiently on diverse supercomputers. It further highlights the potential of LLM-driven agentic systems to perform structured, domain-specific reasoning tasks in scientific and systems-oriented applications.

GPU programs are written in vendor languages that disagree about integer overflow, division by zero, NaN handling, floating-point contraction, data layout and dispatch, so a translated program can compile and still compute something else. We describe CrossTL, an open-source translator that routes ten GPU source languages to eleven targets through CrossGL, a textual hub language, with repository-scale porting, contracts that loaders check, and native parity tests. We define faithful translation as refinement up to rejection under a compile configuration, and test whether a hub that records each source rule and lowers it through one per-target table keeps rules that a syntax-only hub loses. On an internally pre-registered suite of 66 hazard kernels in six languages, run on an Apple GPU through Metal, MoltenVK and WebGPU and on CPU implementations of Vulkan, OpenGL and an emulated Direct3D 12, SPIRV-Cross, naga, Tint, Slang and CrossTL each lose some source rule, and outcomes change with Metal's math mode and between two Vulkan implementations. A rule-carrying prototype of the hub removes 34 of 39 divergences on the rules it carries, against 14 for local fixes to four SPIR-V defects, and refuses where WGSL cannot express a rule. The registered hypothesis that it keeps every rule fails: MoltenVK, a non-conformant Vulkan layer, drops a rule that correct SPIR-V carries natively. On 2,585 programs written by third parties, 31% of CrossTL's translations are usable, established translators produce valid output significantly more often in 31 of 39 comparisons, and carrying the rules changes no target's accepted share by more than 0.2 points. Recording each operation's source rule suffices for the rules tested but is not necessary: one strongest rule would keep them too, at about nine times as many rewrites and 58 more refusals on the corpus.

Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code. We present EyeMulator, a model-agnostic method that injects human visual-attention priors into CodeLLM fine-tuning without architectural changes. EyeMulator distills eye-tracking data into semantic salience and gaze-transition priors, then uses them to reweight token-level training losses. Across six backbones, two data regimes, and three CodeXGLUE tasks, the reported configurations yield positive matched-metric deltas in all 36 model-task-setting cells. Effects are largest for structure-preserving completion and translation, while summarization shows smaller but positive METEOR deltas. Session-mode and component-ablation analyses further show that reading, writing, semantic, and transition-derived priors provide complementary signal. Human-attention artifacts are available at https://zenodo.org/records/17205682.