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

arXiv: https://arxiv.org/abs/2605.06464 · HTML: https://mlsanity.com/paper/2605.06464/

## Key facts

- Cited by 2 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 13 of 13)

- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Human-Written vs. AI-Generated Code: A Large-Scale Study of Defects, Vulnerabilities, and Complexity](https://mlsanity.com/paper/2508.21634/) (2025)
- [Investigating The Smells of LLM Generated Code](https://mlsanity.com/paper/2510.03029/) (2025)
- [Comparing Human and LLM Generated Code: The Jury is Still Out!](https://mlsanity.com/paper/2501.16857/) (2025)
- [Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects](https://mlsanity.com/paper/2502.02368/) (2025)
- [Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests](https://mlsanity.com/paper/2601.03556/) (2026)
- [Early-Stage Prediction of Review Effort in AI-Generated Pull Requests](https://mlsanity.com/paper/2601.00753/) (2026)
- [How do Agents Refactor: An Empirical Study](https://mlsanity.com/paper/2601.20160/) (2026)

## Built on by (most cited first, 2 of 2)

- [Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests](https://mlsanity.com/paper/2609.26847/) (2026)
- [Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase](https://mlsanity.com/paper/2609.29744/) (2026)

## 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.