# Why Are AI Agent Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study

arXiv: https://arxiv.org/abs/2602.00164 · HTML: https://mlsanity.com/paper/2602.00164/

## Key facts

- Cited by 3 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 11 of its 22 references that are in the map.
- First posted on arXiv 29 Jan 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, 11 of 11)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [An Analysis of the Automatic Bug Fixing Performance of ChatGPT](https://mlsanity.com/paper/2301.08653/) (2023)
- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025)
- [Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap](https://mlsanity.com/paper/2410.06107/) (2024)
- [AI in Software Engineering: Perceived Roles and Their Impact on Adoption](https://mlsanity.com/paper/2504.20329/) (2025)
- [A Critical Review of "Automatic Patch Generation Learned from Human-Written Patches": Essay on the Problem Statement and the Evaluation of Automatic Software Repair](https://mlsanity.com/paper/1408.2103/) (2014)
- [Automatic Prediction of Rejected Edits in Stack Overflow](https://mlsanity.com/paper/2210.03281/) (2022)
- [What Drives Issue Resolution Speed? An Empirical Study of Scientific Workflow Systems on GitHub](https://mlsanity.com/paper/2512.18852/) (2025)

## Built on by (most cited first, 3 of 3)

- [How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions](https://mlsanity.com/paper/2605.29442/) (2026)
- [To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing](https://mlsanity.com/paper/2607.28887/) (2026)
- [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)

## Abstract (arXiv)

Autonomous coding agents (e.g., OpenAI Codex, Devin, GitHub Copilot) are increasingly used to generate fix-related pull requests (PRs) in real world software repositories. However, their practical effectiveness depends on whether these contributions are accepted and merged by project maintainers. In this paper, we present an empirical study of AI agent involved fix related PRs, examining both their integration outcomes, latency, and the factors that hinder successful merging. We first analyze 8,106 fix related PRs authored by five widely used AI coding agents from the AIDEV POP dataset to quantify the proportions of PRs that are merged, closed without merging, or remain open. We then conduct a manual qualitative analysis of a statistically significant sample of 326 closed but unmerged PRs, spending approximately 100 person hours to construct a structured catalog of 12 failure reasons. Our results indicate that test case failures and prior resolution of the same issues by other PRs are the most common causes of non integration, whereas build or deployment failures are comparatively rare. Overall, our findings expose key limitations of current AI coding agents in real world settings and highlight directions for their further improvement and for more effective human AI collaboration in software maintenance.