# Migrating Code At Scale With LLMs At Google

arXiv: https://arxiv.org/abs/2504.09691 · HTML: https://mlsanity.com/paper/2504.09691/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 76 references that are in the map.
- First posted on arXiv 13 Apr 2025.

## Builds on (most cited first, 23 of 23)

- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023)
- [CodePlan: Repository-level Coding using LLMs and Planning](https://mlsanity.com/paper/2309.12499/) (2023)
- [An Analysis of the Automatic Bug Fixing Performance of ChatGPT](https://mlsanity.com/paper/2301.08653/) (2023)
- [Automated Unit Test Improvement using Large Language Models at Meta](https://mlsanity.com/paper/2402.09171/) (2024)
- [Using Pre-Trained Models to Boost Code Review Automation](https://mlsanity.com/paper/2201.06850/) (2022)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [Towards Automating Code Review Activities](https://mlsanity.com/paper/2101.02518/) (2021)
- [Using Large Language Models to Generate JUnit Tests: An Empirical Study](https://mlsanity.com/paper/2305.00418/) (2023)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization](https://mlsanity.com/paper/2308.05487/) (2023)
- [Towards Translating Real-World Code with LLMs: A Study of Translating to Rust](https://mlsanity.com/paper/2405.11514/) (2024)
- [Refactoring Programs Using Large Language Models with Few-Shot Examples](https://mlsanity.com/paper/2311.11690/) (2023)
- [A Comparative Analysis of Large Language Models for Code Documentation Generation](https://mlsanity.com/paper/2312.10349/) (2023)
- [Do Developers Update Their Library Dependencies? An Empirical Study on the Impact of Security Advisories on Library Migration](https://mlsanity.com/paper/1709.04621/) (2017)
- [Unprecedented Code Change Automation: The Fusion of LLMs and Transformation by Example](https://mlsanity.com/paper/2402.07138/) (2024)
- [An Empirical Study of Usages, Updates and Risks of Third-Party Libraries in Java Projects](https://mlsanity.com/paper/2002.11028/) (2020)
- [Automatic Library Migration Using Large Language Models: First Results](https://mlsanity.com/paper/2408.16151/) (2024)
- [How is Google using AI for internal code migrations?](https://mlsanity.com/paper/2501.06972/) (2025)
- [Together We Go Further: LLMs and IDE Static Analysis for Extract Method Refactoring](https://mlsanity.com/paper/2401.15298/) (2024)
- [Language Models are Better Bug Detector Through Code-Pair Classification](https://mlsanity.com/paper/2311.07957/) (2023)

## Built on by (most cited first, 14 of 14)

- [CODEMENV: Benchmarking Large Language Models on Code Migration](https://mlsanity.com/paper/2506.00894/) (2025)
- [MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair](https://mlsanity.com/paper/2509.16187/) (2025)
- [Using Copilot Agent Mode to Automate Library Migration: A Quantitative Assessment](https://mlsanity.com/paper/2510.26699/) (2025)
- [Generating High-Quality Datasets for Code Editing via Open-Source Language Models](https://mlsanity.com/paper/2509.25203/) (2025)
- [Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agents](https://mlsanity.com/paper/2602.09944/) (2026)
- [Automatic Qiskit Code Refactoring Using Large Language Models](https://mlsanity.com/paper/2506.14535/) (2025)
- [BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice](https://mlsanity.com/paper/2508.03487/) (2025)
- [SPELL: Synthesis of Programmatic Edits using LLMs](https://mlsanity.com/paper/2602.01107/) (2026)
- [Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents](https://mlsanity.com/paper/2606.15828/) (2026)
- [Automatic Generation of High-Performance RL Environments](https://mlsanity.com/paper/2603.12145/) (2026)
- [SemRep: Generative Code Representation Learning with Code Transformations](https://mlsanity.com/paper/2603.13640/) (2026)
- [Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence](https://mlsanity.com/paper/2605.29054/) (2026)
- [SDAD: Spec-Driven Agentic Development for the AI-Native SDLC](https://mlsanity.com/paper/2608.20341/) (2026)
- [Legacy System Modernization with Coding Agents: A Case Study](https://mlsanity.com/paper/2608.28972/) (2026)

## Abstract (arXiv)

Developers often evolve an existing software system by making internal changes, called migration. Moving to a new framework, changing implementation to improve efficiency, and upgrading a dependency to its latest version are examples of migrations. Migration is a common and typically continuous maintenance task undertaken either manually or through tooling. Certain migrations are labor intensive and costly, developers do not find the required work rewarding, and they may take years to complete. Hence, automation is preferred for such migrations. In this paper, we discuss a large-scale, costly and traditionally manual migration project at Google, propose a novel automated algorithm that uses change location discovery and a Large Language Model (LLM) to aid developers conduct the migration, report the results of a large case study, and discuss lessons learned. Our case study on 39 distinct migrations undertaken by three developers over twelve months shows that a total of 595 code changes with 93,574 edits have been submitted, where 74.45% of the code changes and 69.46% of the edits were generated by the LLM. The developers reported high satisfaction with the automated tooling, and estimated a 50% reduction on the total time spent on the migration compared to earlier manual migrations. Our results suggest that our automated, LLM-assisted workflow can serve as a model for similar initiatives.