Pull Requests as a Training Signal for Repo-Level Code Editing 事件

Pull Requests as a Training Signal for Repo-Level Code Editing arXiv:2602.07457v2 Announce Type: replace-cross Abstract: Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains unclear how much of this capability can be internalised via high-quality training signals. To address this, we propose Clean Pull Request (Cl