Position: Future Research and Challenges Remain Towards AI for Software Engineering

Alex Gu, Naman Jain, Wen-Ding Li, Manish Shetty, Kevin Ellis, Koushik Sen, Armando Solar-Lezama
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81410-81470, 2025.

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 this Paper

BibTeX
@InProceedings{pmlr-v267-gu25e, title = {Position: Future Research and Challenges Remain Towards {AI} for Software Engineering}, author = {Gu, Alex and Jain, Naman and Li, Wen-Ding and Shetty, Manish and Ellis, Kevin and Sen, Koushik and Solar-Lezama, Armando}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {81410--81470}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/gu25e/gu25e.pdf}, url = {https://proceedings.mlr.press/v267/gu25e.html}, 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.} }
Endnote
%0 Conference Paper %T Position: Future Research and Challenges Remain Towards AI for Software Engineering %A Alex Gu %A Naman Jain %A Wen-Ding Li %A Manish Shetty %A Kevin Ellis %A Koushik Sen %A Armando Solar-Lezama %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-gu25e %I PMLR %P 81410--81470 %U https://proceedings.mlr.press/v267/gu25e.html %V 267 %X 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.
APA
Gu, A., Jain, N., Li, W., Shetty, M., Ellis, K., Sen, K. & Solar-Lezama, A.. (2025). Position: Future Research and Challenges Remain Towards AI for Software Engineering. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:81410-81470 Available from https://proceedings.mlr.press/v267/gu25e.html.

Related Material