# LLMigrate: Transforming "Lazy" Large Language Models into Efficient Source Code Migrators

arXiv: https://arxiv.org/abs/2503.23791 · HTML: https://mlsanity.com/paper/2503.23791/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2025.

## Built on by (most cited first, 4 of 4)

- [ENCRUST: Encapsulated Substitution and Agentic Refinement on a Live Scaffold for Safe C-to-Rust Translation](https://mlsanity.com/paper/2604.04527/) (2026)
- [GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks](https://mlsanity.com/paper/2608.03764/) (2026)
- [His2Trans: A Knowledge-Guided Agentic Framework for Project-Level C-to-Rust Migration](https://mlsanity.com/paper/2603.02617/) (2026)
- [Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2609.09233/) (2026)

## Abstract (arXiv)

Rewriting C code in Rust provides stronger memory safety, yet migrating large codebases such as the 32-million-line Linux kernel remains challenging. While rule-based translators (e.g., C2Rust) provide accurate yet largely unsafe Rust programs, recent Large Language Model (LLM) approaches produce more idiomatic, safe Rust programs but frequently exhibit "laziness", omitting significant portions of the target code. To address the issue, in this paper, we present LLMigrate, an LLM-based C-to-Rust translation tool that splits modules into discrete functions, translating them individually, and then reintegrating them. LLMigrate uses static analysis to retain necessary context, pairs GPT-4o (a state-of-the-art LLM) with compiler-driven translation and program-repair techniques for complex core functions, and leverages call-graph-guided translation to ensure consistent interfaces. Evaluations on three representative Linux kernel modules (math, sort, and ramfs) show that LLMigrate requires modifying less than 15% of the target code, significantly outperforming a pure GPT-4o-based migration.