A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI(arxiv.org)58 points by softwaredoug 3 months ago | 36 comments
The End of Code Review: Coding Agents Supersede Human Inspection(arxiv.org)15 points by cribwi 4 months ago | 11 comments
Evaluating AGENTS.md: are they helpful for coding agents?(arxiv.org)175 points by mustaphah 8 months ago | 129 comments
SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI(arxiv.org)102 points by mpweiher 7 months ago | 36 comments