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

French

Commit messages fournissent des enregistrements de changements de code et aident les développeurs à comprendre et à maintenir le logiciel. Pour réduire l'effort manuel impliqué dans leur écriture, les approches de génération de messages commit (CMG) génèrent automatiquement des messages commit qui décrivent les changements de code dans le langage naturel. Les approches CMG existantes traitent généralement CMG comme une tâche autonome et optimisent les messages générés principalement pour la similitude avec les références écrites par les développeurs. Cependant, cet objectif peut ne pas refléter correctement l'utilité pratique des messages commit générés. Cette limitation est importante dans les flux de travail actuels d'ingénierie logicielle assistée par l'IA, où les messages commit sont utilis

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