Documentation-Guided Agentic Codebase Migration from C to Rust
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss architectural intent. We present RustPrint, a documentation-guided agentic framework for repository-level C-to-Rust migration. RustPrint first converts the source repository into architecture-aware documentation and treats it as a migration blueprint capturing module structure, data flow, APIs, and design rationale. Coding agents then use this blueprint to plan crates, implement modules, check compilability, reduce unsafe code, and iteratively refine the translated repository. RustPrint next compares documentation from the Rust output against the source documentation and uses mismatches as repair signals. It also translates and runs source test suites so runtime failures can guide targeted fixes. Experiments on eight real-world C repositories ranging from 11K to 84K LoC show that RustPrint compiles every target under both an open-weight (Kimi-K2-Instruct) and a closed-weight (GPT-5.4) backbone, while prior LLM-based translators (Self-Repair, EvoC2Rust) fail repository-wide. With the open-weight Kimi-K2-Instruct backbone, RustPrint exceeds an agentic Claude Code baseline on feature preservation (93.26% vs. 52.52%) and on cross-evaluation test pass rate (95.17% vs. 79.85%). These results suggest that documentation-guided coordination is a useful direction for scalable codebase migration.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 35 of its 91 references that are in the map. First posted on arXiv 14 May 2026.
Builds on
35 of 91 references.
Closest ancestors · 4
Same direction, newest first
- 2026His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migration3 Mar
- 2025Decoding the Configuration of AI Coding Agents: Insights from Claude Code Projects12 Nov
- 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solving18 May
- 2023ChatDev: Communicative Agents for Software Development16 Jul
Other references · 31
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
- 2025OpenAI GPT-5 System Cardcited by 989
- 2023Teaching Large Language Models to Self-Debugcited by 988
- 2025Kimi K2: Open Agentic Intelligencecited by 567
- 2024RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generationcited by 70
- 2024AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodologycited by 46
- 2024VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learnerscited by 20
- 2025CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilationcited by 19
- 2025EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translationcited by 19
- 2025RPG: A Repository Planning Graph for Unified and Scalable Codebase Generationcited by 19
19 more
- 2025C2SaferRust: Transforming C Projects into Safer Rust with NeuroSymbolic Techniquescited by 18
- 2024Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysiscited by 16
- 2025RustMap: Towards Project-Scale C-to-Rust Migration via Program Analysis and LLMcited by 10
- 2025SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verificationcited by 9
- 2024To Tag, or Not to Tag: Translating C's Unions to Rust's Tagged Unionscited by 8
- 2024Translating C To Rust: Lessons from a User Studycited by 8
- 2024RustRepoTrans: Repository-level Code Translation Benchmark Targeting Rustcited by 6
- 2025Translating Large-Scale C Repositories to Idiomatic Rustcited by 6
- 2023Concrat: An Automatic C-to-Rust Lock API Translator for Concurrent Programscited by 5
- 2024Specification-Driven Code Translation Powered by Large Language Models: How Far Are We?cited by 5
- 2025Forcrat: Automatic I/O API Translation from C to Rust via Origin and Capability Analysiscited by 5
- 2025CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebasescited by 4
- 2019The Android Platform Security Model (2023)cited by 3
- 2024Rusty Linux: Advances in Rust for Linux Kernel Developmentcited by 3
- 2025NL in the Middle: Code Translation with LLMs and Intermediate Representationscited by 3
- 2026ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translationcited by 2
- 2024Bringing Rust to Safety-Critical Systems in Spacecited by 1
- 2024Scylla: Translating an Applicative Subset of C to Safe Rustcited by 1
- 2025C2RUST-BENCH: A Minimized, Representative Dataset for C-to-Rust Transpilation Evaluationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust Transpilation
- 2026From C to Idiomatic Rust: A Ship-of-Theseus Agentic Translation ↗
- 2026AdaTrans: Automated C to Rust Transformation via Error-Adaptive Repair ↗
- 2026Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT
- 2026Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents
- 2026Towards Reliable C-to-Rust Translation with Rule-Guided Reasoning and Reinforcement Learning
- 2026Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
- 2026Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies