Newest papers

Beyond Similarity-Based Generation: Guiding Commit Message Generation with Issue-Commit Traceability

Chunying Zhou, Gong Chen, Xiaoyuan Xie, Yi Song, Yuxuan Yang, Peng He · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25303 · cited by 0 works (OpenAlex) · open-access PDF

Korean

헌신 메시지는 코드 변경 기록을 제공하고 개발자가 소프트웨어를 이해하고 유지하는 데 도움이됩니다. 작성에 관련된 수동 노력을 줄이기 위해, 헌신 메시지 생성 (CMG) 접근 방식은 자연 언어로 코드 변경을 설명하는 헌신 메시지를 자동으로 생성합니다. 기존 CMG 접근 방식은 일반적으로 CMG를 독립적 인 작업으로 취급하고 생성 된 메시지를 주로 개발자가 작성한 참조와 유사함을 위해 최적화합니다. 그러나이 목표는 생성 된 헌신 메시지의 실용적인 유용성을 적절하게 반영하지 않을 수 있습니다. 이 제한은 현재 AI 지원 소프트웨어 엔지니어링 워크플로우에서, 헌신 메시지가 다른 소프트웨어 엔지니어링 활동을 제공하기 위해 공유 정보

Machine translation (Meta M2M100); the English original follows.

Abstract

Commit messages provide records of code changes and help developers understand and maintain software. To reduce the manual effort involved in writing them, commit message generation (CMG) approaches automatically generate commit messages that describe code changes in natural language. Existing CMG approaches generally treat CMG as a standalone task and optimize generated messages primarily for similarity to developer-written references. However, this objective may not properly reflect the practical usefulness of generated commit messages. This limitation matters in current AI-assisted software engineering workflows, where commit messages are used as shared information to serve different software engineering activities. To fill this gap, we propose TraceMsg, which uses issue-commit traceability, a representative software engineering activity, to guide commit message generation. TraceMsg is a collaborative multi-agent framework that coordinates message generation, traceability reasoning, and feedback-guided refinement, allowing generated messages to serve traceability while using reasoning feedback to guide issue-conditioned refinement. We evaluate TraceMsg on six open-source projects. The experimental results show that TraceMsg achieves an average Hit@1 of 0.893 and an MRR of 0.911, improving Hit@1 and MRR by 13.16% and 38.75%, respectively, over the best baseline for each metric.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Commit, Traceability, Computer science, Software, Task (project management), Software engineering

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange