{"ID":2823298,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00753","arxiv_id":"2601.00753","title":"Early-Stage Prediction of Review Effort in AI-Generated Pull Requests","abstract":"As AI coding agents evolve from autocomplete tools to autonomous \"AI workforce\" teammates, they introduce a critical new bottleneck: human maintainers must now manage complex interaction loops rather than just reviewing code. Analyzing 33,707 agent-authored PRs, we uncover a stark two-regime reality: agents excel at narrow automation (28.3% of PRs merge instantly), but frequently fail at iterative refinement, leading to \"ghosting\" (abandonment) when faced with subjective feedback. This creates a hidden \"attention tax\" on maintainers. We introduce a creation-time Circuit Breaker model to predict high-maintenance PRs before human review begins. By leveraging simple static complexity cues (e.g., file types, patch size), our model identifies the \"expensive tail\" of contributions with AUC 0.96, enabling a gated triage process. At a 20% review budget, this approach captures 69% of the high-effort PRs, effectively allowing maintainers to fast-fail costly, low-quality agent contributions while fast-tracking simple fixes.","short_abstract":"As AI coding agents evolve from autocomplete tools to autonomous \"AI workforce\" teammates, they introduce a critical new bottleneck: human maintainers must now manage complex interaction loops rather than just reviewing code. Analyzing 33,707 agent-authored PRs, we uncover a stark two-regime reality: agents excel at na...","url_abs":"https://arxiv.org/abs/2601.00753","url_pdf":"https://arxiv.org/pdf/2601.00753v2","authors":"[\"Dao Sy Duy Minh\",\"Huynh Trung Kiet\",\"Nguyen Lam Phu Quy\",\"Pham Phu Hoa\",\"Tran Chi Nguyen\",\"Nguyen Dinh Ha Duong\",\"Truong Bao Tran\"]","published":"2026-01-02T17:18:01Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[]","has_code":false}