mlsanityData to 14 Oct 2026

Migrating Code At Scale With LLMs At Google

arXiv 2504.09691 ↗First posted 13 Apr 2025cs.SE cs.AIcited by 14

Not on the map. Why?

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.

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

23 of 76 references.

References · 23

  1. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  2. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  3. 2020Unsupervised Translation of Programming Languagescited by 263
  4. 2023An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generationcited by 194
  5. 2023CodePlan: Repository-level Coding using LLMs and Planningcited by 140
  6. 2023An Analysis of the Automatic Bug Fixing Performance of ChatGPTcited by 110
  7. 2024Automated Unit Test Improvement using Large Language Models at Metacited by 75
  8. 2022Using Pre-Trained Models to Boost Code Review Automationcited by 63
  9. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  10. 2021Towards Automating Code Review Activitiescited by 54
  11. 2023Using Large Language Models to Generate JUnit Tests: An Empirical Studycited by 53
  12. 2024What's Wrong with Your Code Generated by Large Language Models? An Extensive Studycited by 53
11 more
  1. 2023A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localizationcited by 50
  2. 2024Towards Translating Real-World Code with LLMs: A Study of Translating to Rustcited by 35
  3. 2023Refactoring Programs Using Large Language Models with Few-Shot Examplescited by 28
  4. 2023A Comparative Analysis of Large Language Models for Code Documentation Generationcited by 24
  5. 2017Do Developers Update Their Library Dependencies? An Empirical Study on the Impact of Security Advisories on Library Migrationcited by 23
  6. 2024Unprecedented Code Change Automation: The Fusion of LLMs and Transformation by Examplecited by 15
  7. 2020An Empirical Study of Usages, Updates and Risks of Third-Party Libraries in Java Projectscited by 12
  8. 2024Automatic Library Migration Using Large Language Models: First Resultscited by 9
  9. 2025How is Google using AI for internal code migrations?cited by 6
  10. 2024Together We Go Further: LLMs and IDE Static Analysis for Extract Method Refactoringcited by 5
  11. 2023Language Models are Better Bug Detector Through Code-Pair Classificationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 8.

14 papers.

Sort:

By area:

  1. 2025CODEMENV: Benchmarking Large Language Models on Code Migrationcited by 13
  2. 2025MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repaircited by 4
  3. 2025Using Copilot Agent Mode to Automate Library Migration: A Quantitative Assessmentcited by 3
  4. 2025Generating High-Quality Datasets for Code Editing via Open-Source Language Modelscited by 2
  5. 2026Environment-in-the-Loop: Rethinking Code Migration with LLM-based Agentscited by 2
  6. 2025Automatic Qiskit Code Refactoring Using Large Language Modelscited by 1
  7. 2025BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practicecited by 1
  8. 2026SPELL: Synthesis of Programmatic Edits using LLMscited by 1
  9. 2026Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agentscited by 1
  10. 2026Automatic Generation of High-Performance RL Environmentscited by 0
  11. 2026SemRep: Generative Code Representation Learning with Code Transformationscited by 0
  12. 2026Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalencecited by 0
2 more
  1. 2026SDAD: Spec-Driven Agentic Development for the AI-Native SDLCcited by 0
  2. 2026Legacy System Modernization with Coding Agents: A Case Studycited by 0