mlsanityData to 7 Oct 2026

To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study

arXiv 2605.06464 ↗First posted 7 May 2026cs.SEcited by 2

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

LLM-based autonomous coding agents have reshaped software development. While these agents excel at code generation, open questions persist about the long-term maintainability of AI-generated code. This study empirically investigates the maintenance extent, human involvement, and modification types of AI-generated files versus human-authored code. Using the AIDev dataset of AI-generated pull requests and GitHub, we analyzed over 1,000 files and approximately 3,200 changes from 100 popular repositories. Our findings show that: (i) AI-generated files receive less frequent maintenance than human-authored code, with updates affecting only a small fraction of file size; (ii) the most frequent modifications to AI code are feature extensions, whereas human updates focus on bug fixes, and (iii) human developers perform the large majority of this maintenance.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 13 of its 28 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

13 of 28 references.

Closest ancestors · 4

Same direction, newest first

  1. 2026Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests7 Jan
  2. 2026Early-Stage Prediction of Review Effort in AI-Generated Pull Requests2 Jan
  3. 2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub18 Sep
  4. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul

Other references · 9

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  2. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 417
  3. 2022Do Users Write More Insecure Code with AI Assistants?cited by 186
  4. 2025Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivitycited by 93
  5. 2025Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexitycited by 16
  6. 2025Investigating The Smells of LLM Generated Codecited by 9
  7. 2025Comparing Human and LLM Generated Code: The Jury is Still Out!cited by 6
  8. 2025Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projectscited by 4
  9. 2026How do Agents Refactor: An Empirical Studycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requestscited by 0
  2. 2026Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebasecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
  2. 2026Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs
  3. 2026Is Agent Code Less Maintainable Than Human Code?
  4. 2026How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests
  5. 2026AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality
  6. 2024Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios
  7. 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
  8. 2026How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study