# SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification

arXiv: https://arxiv.org/abs/2503.12511 · HTML: https://mlsanity.com/paper/2503.12511/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Code Translation with Compiler Representations](https://mlsanity.com/paper/2207.03578/) (2022)
- [A Survey of Symbolic Execution Techniques](https://mlsanity.com/paper/1610.00502/) (2016)
- [Towards Translating Real-World Code with LLMs: A Study of Translating to Rust](https://mlsanity.com/paper/2405.11514/) (2024)
- [LongGenBench: Long-context Generation Benchmark](https://mlsanity.com/paper/2410.04199/) (2024)
- [VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners](https://mlsanity.com/paper/2404.18852/) (2024)
- [C2SaferRust: Transforming C Projects into Safer Rust with NeuroSymbolic Techniques](https://mlsanity.com/paper/2501.14257/) (2025)
- [Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis](https://mlsanity.com/paper/2412.14234/) (2024)
- [Ownership guided C to Rust translation](https://mlsanity.com/paper/2303.10515/) (2023)

## Built on by (most cited first, 9 of 9)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories](https://mlsanity.com/paper/2604.07341/) (2026)
- [Verifier-Guided Code Translation via Meta-Step Decoding](https://mlsanity.com/paper/2605.17626/) (2026)
- [His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migration](https://mlsanity.com/paper/2603.02617/) (2026)
- [SoK: Understanding (New) Security Issues Across AI4Code Use Cases](https://mlsanity.com/paper/2512.18456/) (2025)
- [Documentation-Guided Agentic Codebase Migration from C to Rust](https://mlsanity.com/paper/2605.14634/) (2026)
- [Towards Reliable C-to-Rust Translation with Rule-Guided Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2607.19966/) (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)
- [Translator vs. Challenger: Adversarial Agentic Learning for C-to-Rust Translation](https://mlsanity.com/paper/2609.15381/) (2026)

## Abstract (arXiv)

Translating software written in C to Rust has significant benefits in improving memory safety. However, manual translation is cumbersome, error-prone, and often produces unidiomatic code. Large language models (LLMs) have demonstrated promise in producing idiomatic translations, but offer no correctness guarantees. We propose SACTOR, an LLM-driven C-to-Rust translation tool that employs a two-step process: an initial "unidiomatic" translation to preserve semantics, followed by an "idiomatic" refinement to align with Rust standards. To validate correctness of our function-wise incremental translation that mixes C and Rust, we use end-to-end testing via the foreign function interface. We evaluate SACTOR on 200 programs from two public datasets and on two more real-world scenarios (a 50-sample subset of CRust-Bench and the libogg library), comparing multiple LLMs. Across datasets, SACTOR delivers high end-to-end correctness and produces safe, idiomatic Rust with up to 7 times fewer Clippy warnings; On CRust-Bench, SACTOR achieves an average (across samples) of 85% unidiomatic and 52% idiomatic success, and on libogg it attains full unidiomatic and up to 78% idiomatic coverage on GPT-5.