Early-Stage Prediction of Review Effort in AI-Generated Pull Requests

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Minh, Dao Sy Duy, Kiet, Huynh Trung, Quy, Nguyen Lam Phu, Hoa, Pham Phu, Nguyen, Tran Chi, Duong, Nguyen Dinh Ha, Tran, Truong Bao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915757288325120
author Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Hoa, Pham Phu
Nguyen, Tran Chi
Duong, Nguyen Dinh Ha
Tran, Truong Bao
author_facet Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Hoa, Pham Phu
Nguyen, Tran Chi
Duong, Nguyen Dinh Ha
Tran, Truong Bao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00753
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Early-Stage Prediction of Review Effort in AI-Generated Pull Requests
Minh, Dao Sy Duy
Kiet, Huynh Trung
Quy, Nguyen Lam Phu
Hoa, Pham Phu
Nguyen, Tran Chi
Duong, Nguyen Dinh Ha
Tran, Truong Bao
Software Engineering
D.2.7
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.
title Early-Stage Prediction of Review Effort in AI-Generated Pull Requests
topic Software Engineering
D.2.7
url https://arxiv.org/abs/2601.00753