RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.