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

• URL: http://arxiv.org/abs/2605.06464v2
• Date: Sat, 09 May 2026 06:52:52 GMT
• Title: To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study
• Abstract summary: This study empirically investigates the maintenance extent, human involvement, and modification types of AI-generated files versus human-authored code.<n>We analyzed over 1,000 files and approximately 3,200 changes from 100 popular repositories.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance [10.648969524722448]
  Recent work seeks to automate skill curation, but it largely evaluates against automated baselines and treats human maintenance as an unmeasured bottleneck.<n>We mine the full commit histories of five public AI-skill repositories, a purposive sample of AI-tooling organizations, covering 873 commits, 143 skill files, and 254 substantive post-creation edits from October 2025 to June 2026.<n>First, every substantive edit is authored or merged through a named human account, while 62% carry an AI co-author trailer, with large repository-level variation.
  arXiv  Detail & Related papers  (2026-09-04T19:18:18Z)
• On Automated and Explainable Provenance of AI-Generated Code [56.818202904805446]
  We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
  arXiv  Detail & Related papers  (2026-08-03T14:50:31Z)
• Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments [7.213400161126317]
  We analyze 35,361 GitHub code comments that explicitly reference AI use and their associated code blocks.<n>We first open-code 500 unique comments and code blocks to derive a taxonomy of AI-assisted development activities.<n>We then annotate the full dataset using two LLM-based classifiers and aggregate predictions with Dawid-Skene expectation-maximization.
  arXiv  Detail & Related papers  (2026-06-05T02:37:44Z)
• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• SWE-chat: Coding Agent Interactions From Real Users in the Wild [70.18158706281724]
  SWE-chat is the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild.<n>The dataset currently contains 6,000 sessions, comprising more than 63,000 user prompts and 355,000 agent tool calls.
  arXiv  Detail & Related papers  (2026-04-22T17:08:19Z)
• Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild [13.35459155979355]
  We build a dataset of 304,362 verified AI-authored commits from 6,275 GitHub repositories.<n>We identify 484,606 distinct issues, and that code smells are by far the most common type, accounting for 89.1% of all issues.<n>These findings show that AI-generated code can introduce long-term maintenance costs into real software projects.
  arXiv  Detail & Related papers  (2026-03-30T15:38:05Z)
• AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality [0.0]
  The rapid adoption of AI coding agents for software development has raised important questions about the quality and maintainability of the code they produce.<n>This data mining challenge focuses on AIDev, the first large-scale, openly available dataset capturing agent-pull requests from real-world GitHub repositories.<n>We identified 364 maintainability and security-related build smells across varying severity levels, indicating that AI-generated build code can introduce quality issues.
  arXiv  Detail & Related papers  (2026-01-23T15:40:28Z)
• Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source [3.6525095710982924]
  A prevailing hypothesis suggests that code is "disposable", meaning it is merged quickly but discarded shortly thereafter.<n>We investigate this hypothesis through survival analysis of 201 open-source projects, tracking over 200,000 code remediation units authored by AI agents versus humans.
  arXiv  Detail & Related papers  (2026-01-23T15:00:46Z)
• AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software [12.708926174194199]
  We present the first large-scale empirical study of AI-generated code (AIGCode) in the wild.<n>We build a high-precision detection pipeline and a benchmark to distinguish AIGCode from human-written code.<n>This lets us label commits, files, and functions along a human/AI axis and trace how AIGCode moves through projects and vulnerability life cycles.
  arXiv  Detail & Related papers  (2025-12-21T02:26:29Z)
• Toward Training Superintelligent Software Agents through Self-Play SWE-RL [66.11447353341926]
  Self-play SWE-RL is a first step toward training paradigms for superintelligent software agents.<n>Our approach takes minimal data assumptions, only requiring access to sandboxed repositories with source code and installed dependencies.<n>Our results, albeit early, suggest a path where agents autonomously gather extensive learning experiences from real-world software repositories.
  arXiv  Detail & Related papers  (2025-12-21T00:49:40Z)
• AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humans [46.56091965723774]
  Fine-tuning large language models for code editing has typically relied on mining commits and pull requests.<n>We present AgentPack, a corpus of 1.3M code edits co-authored by Claude Code, OpenAI Codex, and Cursor Agent.<n>We show that models fine-tuned on AgentPack can outperform models trained on prior human-only commit corpora.
  arXiv  Detail & Related papers  (2025-09-26T05:28:22Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science [70.1638335489284]
  High-level machine learning engineering tasks remain labor-intensive and iterative.<n>We introduce R&D-Agent, a comprehensive, decoupled, and framework that formalizes the machine learning process.<n>R&D-Agent defines the MLE into two phases and six components, turning agent design for MLE into a principled, testable process.
  arXiv  Detail & Related papers  (2025-05-20T06:07:00Z)
• Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios [13.949319911378826]
  This study evaluated 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues.<n>No single agent dominated, with 170 issues unresolved, indicating room for improvement.<n>Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities.<n>Some agents increased code complexity, many reduced code duplication and minimized code smells.
  arXiv  Detail & Related papers  (2024-10-16T11:33:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.