シェア

ソフトウェア工学研究室の田中 英武さん(D1)らが、23rd International Mining Software Repositories Conference(MSR2026)において Distinguished Mining Challenge Paper Awardを受賞しました。(2026/4/14)

　23rd International Conference on Mining Software Repositories（MSR 2026）は、2026年4月13日〜14日の期間、ブラジル（リオデジャネイロ）で開催されました。
  
  • 受賞者 Awardee:
    　Sien Reeve O. Peralta (Waseda Univ.), Fumika Hoshi (Waseda Univ.), Hironori Washizaki (Waseda Univ.), Naoyasu Ubayashi (Waseda Univ.), Inase Kondo (The University of Osaka), Yoshiki Higo (The University of Osaka), Hiroki Mukai (Ritsumeikan Univ.), Norihiro Yoshida (Ritsumeikan Univ.), Kazuki Kusama (Kyusyu Univ.), Hidetake Tanaka (D1, NAIST), Youmei Fan (NAIST)
    image 　　　　田中 英武(D1)さん
     
    　　
  • 研究テーマ Research theme:
    　“Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study”
    　AI coding agents increasingly submit pull requests (Agentic-PRs) to open-source repositories, yet their performance is commonly assessed using merge and rejection outcomes alone. We hypothesized that these outcome labels do not reliably reflect agent capability without considering review interactions. To test this, we conducted a decision-oriented analysis of 11,048 closed Agentic Pull Requests, refined to 9,799 human-reviewed PRs, and manually inspected 717 representative cases to recover decision rationale from interaction artifacts. We found that rejection outcomes substantially overstate agent error: only 35.7% of rejected PRs reflected clear agentic failures, while 31.2% were driven by workflow constraints and 33.1% lacked observable decision rationale. Among merged PRs, 15.4% required explicit reviewer involvement through feedback or direct commits, and 5.5% showed no visible interaction trace. We further observed systematic differences across agents, with Copilot and Devin more often embedded in reviewer-mediated workflows, while Codex and Cursor PRs were typically merged with minimal interaction. These results reject the assumption that PR outcomes alone capture agent performance and demonstrate the need for interaction-aware evaluation grounded in review behavior.


  • 受賞者のコメント Awardee's voice
  •  このたびは、このような栄誉ある賞をいただき、大変光栄です。本研究の成果は、研究チームの皆様と取り組むことによって成し遂げられたものであり、ご指導いただいた先生方ならびに研究チームの皆様に心より感謝申し上げます。今回の受賞を励みに、今後もより一層研究活動に励んでまいります。  
  •  
  • 外部リンク Links to：
    MSR2026 HP：https://2026.msrconf.org

>> ソフトウェア工学 Software Engineering lab.

CLOSE