Beyond Similarity-Based Generation: Membimbing Generasi Pesan Komitmen dengan Traceability Issue-Commit / Beyond Similarity-Based Generation: Guiding Commit Message Generation with Issue-Commit Traceability (2026) (Indonesian)

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

Indonesian

Pemberitahuan komitmen menyediakan catatan perubahan kode dan membantu pengembang memahami dan mempertahankan perangkat lunak. Untuk mengurangi upaya manual yang terlibat dalam menulisnya, pendekatan komisi pesan (CMG) secara otomatis menghasilkan pesan komisi yang menggambarkan perubahan kode dalam bahasa alami. Pendekatan CMG yang ada umumnya memperlakukan CMG sebagai tugas independen dan mengoptimalkan pesan yang dihasilkan terutama untuk kesamaan dengan referensi yang ditulis oleh pengembang. Namun, tujuan ini mungkin tidak secara tepat mencerminkan kegunaan praktis dari pesan komisi yang dihasilkan. Pembatasan ini penting dalam alur kerja teknik perangkat lunak yang didukung AI saat ini, di mana pesan komisi digunakan sebagai informasi bersama untuk melayani kegiatan rekayasa perangkat lunak yang berbeda. Untuk mengisi kesenjangan ini, kami mengusulkan TraceMsg, yang menggunakan traceability masalah yang ditulis oleh pengembang, aktivitas rekayasa perangkat

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.

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25303, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt