Towards Reliable C-to-Rust Translation with Rule-Guided Reasoning and Reinforcement Learning

• URL: http://arxiv.org/abs/2607.19966v1
• Date: Wed, 22 Jul 2026 09:50:01 GMT
• Title: Towards Reliable C-to-Rust Translation with Rule-Guided Reasoning and Reinforcement Learning
• Abstract summary: Leveraging large language models for automated C-to-Rust translation has emerged as a promising direction.<n>We propose a Translation fRAmework Via rule-guided reasoning and rEinforcement Learning, namely TRAVEL, consisting of two modules.<n>The first module employs Monte Carlo Tree Search (MCTS)-based reasoning path construction guided by Rust-specific rules.<n>The second module introduces reinforcement learning that couples execution feedback with reasoning-quality signals, encouraging the model to construct reasoning paths that accurately capture program semantics.
• Score: 21.45219780181232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The migration of legacy C programs to Rust has become an important direction for improving software memory safety while alleviating the high cost of manual rewriting. Leveraging large language models (LLMs) for automated C-to-Rust translation has emerged as a promising direction. However, existing LLM-based approaches remain limited. On the one hand, LLMs exhibit limited capability in identifying Rust-specific rules, and inadequate handling of Rust syntax often results in incorrect translations. On the other hand, existing LLMs often struggle to accurately capture the semantics of complex code, resulting in incorrect translations. To address these challenges, we propose a Translation fRAmework Via rule-guided reasoning and rEinforcement Learning, namely TRAVEL, consisting of two modules. The first module employs Monte Carlo Tree Search (MCTS)-based reasoning path construction guided by Rust-specific rules, steering the search toward translation steps that respect the syntactic rules that LLMs frequently violate. The second module introduces reinforcement learning that couples execution feedback with reasoning-quality signals, encouraging the model to construct reasoning paths that accurately capture program semantics, thereby ensuring that the generated Rust code preserves the intended behavior of the original C program. We evaluate TRAVEL on three datasets: xCodeEval (a public benchmark), OS-Bench (functions collected from the Linux kernel), and HW-Bench (an industrial dataset from Huawei). On xCodeEval, TRAVEL outperforms all baselines across three backbone LLMs. In particular, compared to the strongest prompting baseline IRENE, TRAVEL improves computational accuracy (CA) by 26.22% and compilation success rate (CSR) by 18.77%. On HW-Bench and OS-Bench, TRAVEL further improves CSR by 18.28% and 16.51%, respectively, while reducing unsafe rate (UR) by 13.06% and 13.08%, respectively.

Related papers

• The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis [50.473217152006875]
  MIMIC is a framework that leverages executable code as a rigorous medium for reasoning data synthesis.<n>MIMIC transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation.<n>Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks.
  arXiv  Detail & Related papers  (2026-09-13T17:04:16Z)
• A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination [51.06539604709775]
  We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views.<n>A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory.
  arXiv  Detail & Related papers  (2026-08-05T14:01:10Z)
• C2RustXW: Program-Structure-Aware C-to-Rust Translation via Program Analysis and LLM [16.098065606505983]
  tool is a program-structure-aware C-to-Rust translation approach that integrates program analysis with Large Language Models (LLMs)<n>tool achieves 100% syntactic correctness on CodeNet and 97.78% on GitHub, while significantly reducing code size (up to 43.70%) and unsafe usage (to 5.75%)<n>At the project level, tool achieves perfect syntactic correctness and an average semantic correctness of 78.87%, demonstrating its effectiveness for practical and scalable C-to-Rust migration.
  arXiv  Detail & Related papers  (2026-03-30T17:07:11Z)
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation [52.62655622099456]
  We propose reinforcement learning with verifiable reference-based rewards (RLVRR)<n>Instead of checking the final answer, RLVRR extracts an ordered linguistic signal from high-quality references (i.e., reward chain)<n>In this way, RLVRR decomposes rewards into two dimensions: content, which preserves deterministic core concepts, and style, which evaluates adherence to stylistic properties.
  arXiv  Detail & Related papers  (2026-01-26T14:39:58Z)
• Context-Guided Decompilation: A Step Towards Re-executability [50.71992919223209]
  Binary decompilation plays an important role in software security analysis, reverse engineering and malware understanding.<n>Recent advances in large language models (LLMs) have enabled neural decompilation, but the generated code is typically only semantically plausible.<n>We propose ICL4Decomp, a hybrid decompilation framework that leverages in-context learning (ICL) to guide LLMs toward generating re-executable source code.
  arXiv  Detail & Related papers  (2025-11-03T17:21:39Z)
• Integrating Rules and Semantics for LLM-Based C-to-Rust Translation [34.61632926526051]
  We propose IRENE, an LLM-based framework that integrates RulEs aNd sEmantics to enhance translation.<n> IRENE consists of three modules: 1) a rule-augmented retrieval module that selects relevant translation examples based on rules generated from a static analyzer developed by us, thereby improving the handling of Rust rules; 2) a structured summarization module that produces a structured summary for guiding LLMs to enhance the semantic understanding of C code; 3) an error-driven translation module that leverages compiler diagnostics to iteratively refine translations.
  arXiv  Detail & Related papers  (2025-08-09T10:41:03Z)
• EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation [17.560908544319094]
  EvoC2Rust is an automated framework for converting complete C projects to equivalent Rust ones.<n>It employs a skeleton-guided translation strategy for project-level translation.
  arXiv  Detail & Related papers  (2025-08-06T10:31:23Z)
• Large Language Model-Powered Agent for C to Rust Code Translation [2.182572303351317]
  A modern system programming language, Rust, has emerged as a memory-safe alternative to the C programming language.<n>Applying the agentic capability for the C-to-Rust translation introduces distinct challenges.<n>Unlike math or commonsense QA, the intermediate steps required for C-to-Rust are not well-defined.<n>We propose a novel intermediate step, the Virtual Fuzzing-based equivalence Test (VFT), and an agentic planning framework, the LLM-powered Agent for C-to-Rust code translation (LAC2R)
  arXiv  Detail & Related papers  (2025-05-21T01:26:23Z)
• LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators [21.114491141763647]
  Rewriting C code in Rust provides stronger memory safety, yet migrating larges such as the 32-million-line Linux kernel remains challenging.<n>Recent Large Language Model (LLM) approaches produce more idiomatic, safe Rust programs but frequently exhibit "laziness"<n>LLM-based C-to-Rust translation tool splits modules into discrete functions, translating them individually, and then reintegrating them.
  arXiv  Detail & Related papers  (2025-03-31T07:09:07Z)
• RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rust [50.65321080814249]
  RustRepoTrans is the first repository-level context code translation benchmark targeting incremental translation.<n>We evaluate seven representative LLMs, analyzing their errors to assess limitations in complex translation scenarios.
  arXiv  Detail & Related papers  (2024-11-21T10:00:52Z)
• Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning [57.323716555996114]
  Off-target translation remains an unsolved problem, especially for low-resource languages. Recent works have either designed advanced prompting strategies to highlight the functionality of translation instructions or exploited the in-context learning ability of LLMs. In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
  arXiv  Detail & Related papers  (2024-03-21T13:47:40Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)

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.