# Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests

arXiv: https://arxiv.org/abs/2609.26847 · HTML: https://mlsanity.com/paper/2609.26847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 22 Sep 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, 18 of 18)

- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [Agentic Much? Adoption of Coding Agents on GitHub](https://mlsanity.com/paper/2601.18341/) (2026)
- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild](https://mlsanity.com/paper/2603.28592/) (2026)
- [How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests](https://mlsanity.com/paper/2601.17581/) (2026)
- [Understanding Dominant Themes in Reviewing Agentic AI-authored Code](https://mlsanity.com/paper/2601.19287/) (2026)
- [Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study](https://mlsanity.com/paper/2605.22534/) (2026)
- [Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests](https://mlsanity.com/paper/2601.04886/) (2026)
- [Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source](https://mlsanity.com/paper/2601.16809/) (2026)
- [Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study](https://mlsanity.com/paper/2602.00164/) (2026)
- [How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses](https://mlsanity.com/paper/2602.17084/) (2026)
- [Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap](https://mlsanity.com/paper/2605.04532/) (2026)
- [Mea culpa: How developers fix their own simple bugs differently from other developers](https://mlsanity.com/paper/2103.11894/) (2021)
- [Do practitioners intentionally self-fix Technical Debt and why?](https://mlsanity.com/paper/2106.11904/) (2021)
- [These Aren't the Reviews You're Looking For How Humans Review AI-Generated Pull Requests](https://mlsanity.com/paper/2605.02273/) (2026)
- [To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study](https://mlsanity.com/paper/2605.06464/) (2026)
- [Does it matter who pays back Technical Debt? An empirical study of self-fixed TD](https://mlsanity.com/paper/2110.05928/) (2021)
- [Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice](https://mlsanity.com/paper/2604.04059/) (2026)

## Abstract (arXiv)

AI coding agents now author a large share of pull requests (PRs) merged into popular open-source projects. A merged agent PR is usually considered finished work; yet, prior studies have reported issues in agent code after the merge (e.g., code smells and static-analysis issues). However, little is known about how often a merged agent PR is fixed afterward, and who actually authors the fixing. In this paper, we follow 6,774 merged agent PRs across five AI coding agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code) from the AIDev-pop dataset (open-source repositories with at least 500 stars) into their follow-up fixes, against a baseline of 5,044 contemporaneous human PRs from the same repositories. We link each merge to its candidate fixes, verify every candidate with human annotators and an LLM judge that matches human-level agreement (binary Cohen's Kappa=0.78 against a human-human K=0.77, Direct-fix precision 90%), and attribute the fixing work at the PR and the commit level. Our findings show that (1) merged agent PRs attract verified fixes at 1.62 times the odds of merged human PRs in the same repositories over the same period of time; (2) 69.6% of verified fixes in agent merges come from the same agent; and (3) 76.4% of the verified fix PRs are agent-authored throughout all commits. These results show that agents currently largely finish their own job, but their merges still require fixing more often than human merges.