RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair

Excerpt

arXiv:2610.04658v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly reuse prior experience, but most approaches assume that problems and solutions are already aligned. Software histories rarely provide this alignment: a pull request (PR) may contain multiple continuous integration (CI) problems, failed attempts, reverted edits, and unrelated changes, obscuring which changes resolve each problem. We present RETRACE, a framework for reconstructing problem-level repair