paper-with-me

Papers

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

2026-07-07 · Ruoyu Wang, Jierun Chen, Shaowei Wang, Chaofan Tao, Sidi Yang, Yuxin Jiang, Kim-Hui Yap, Lifeng Shang, Xiaohui Li, Haoli Bai hf

Coding agents increasingly generate pull requests (PRs) for real-world software issues, yet one-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or revision. We introduce SWE-Review, a framework for closing this loop with agentic code review. Given an issue and an AI-generated PR, a reviewer agent explores the repository, decides whether the PR should be accepted, and provides structured feedback for revision. We evaluate this setting with our proposed SWE-Review-Bench to measure both review correctness and downstream revision usefulness. We further curate SWE-Review-Traj dataset to study broader applications of agentic review and fill the data-scarcity gap for open reviewer training. Experiments show that agentic review continuously improves PRs through a generate-review-revise loop, outperforms single-turn fixed-context review in both decision accuracy and resolve rate after revision, transfers beyond review to improve issue-resolution models, and enables effective and efficient test-time scaling. These results position agentic code review as a practical mechanism for moving AI coding agents from one-shot PR generation toward closed-loop issue resolution.

📄 PDF Abstract BibTeX arXiv:2607.06065

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Agentic Discovery: Closing the Loop with Cooperative Agents

2025-10-15 · J. Gregory Pauloski, Kyle Chard, Ian T. Foster arxiv

As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, gene…

AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification

2026-07-30 · Haobo Li, Eunseo Jung, Wenxiao Zhao, Feng Liu 외 arxiv

Recent advances in large language models (LLMs) have enabled AI systems to assist scientific research and peer review. However, an essential capability for reliable AI-assisted scientific workflows remains underexplored:…

SWEnergy: An Empirical Study on Energy Efficiency in Agentic Issue Resolution Frameworks with SLMs

2025-12-10 · Arihant Tripathy, Ch Pavan Harshit, Karthik Vaidhyanathan arxiv

Context. LLM-based autonomous agents in software engineering rely on large, proprietary models, limiting local deployment. This has spurred interest in Small Language Models (SLMs), but their practical effectiveness and …

Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery

2026-07-05 · Kyunghoon Hur, Chihun Lee arxiv

Agentic AI-for-Science can automate ideation, planning, and analysis, but final validation still depends on real experiments. A self-driving lab (SDL) can execute those experiments, yet the loop still has bottlenecks: th…

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

2026-03-20 · Xiang Zhuang, Chenyi Zhou, Kehua Feng, Zhihui Zhu 외 arxiv

Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most curr…