Tasks, Challenges, and Paths Towards AI for Software Engineering
Abstract
AI for software engineering has made remarkable progress, becoming a notable success within generative AI. Despite this, achieving fully automated software engineering is still a significant challenge, requiring research efforts across both academia and industry. In this position paper, our goal is threefold. First, we provide a taxonomy of measures and tasks to categorize work towards AI software engineering. Second, we outline the key bottlenecks permeating today's approaches. Finally, we highlight promising paths towards making progress on these bottlenecks to guide future research in this rapidly maturing field.
Cite
Text
Gu et al. "Tasks, Challenges, and Paths Towards AI for Software Engineering." ICLR 2025 Workshops: VerifAI, 2025.Markdown
[Gu et al. "Tasks, Challenges, and Paths Towards AI for Software Engineering." ICLR 2025 Workshops: VerifAI, 2025.](https://mlanthology.org/iclrw/2025/gu2025iclrw-tasks-a/)BibTeX
@inproceedings{gu2025iclrw-tasks-a,
title = {{Tasks, Challenges, and Paths Towards AI for Software Engineering}},
author = {Gu, Alex and Jain, Naman and Li, Wen-Ding and Shetty, Manish and Shao, Yijia and Li, Ziyang and Yang, Diyi and Sen, Koushik and Ellis, Kevin and Solar-Lezama, Armando},
booktitle = {ICLR 2025 Workshops: VerifAI},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/gu2025iclrw-tasks-a/}
}