AI for software engineering: from probable to provable
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913056055885824 |
|---|---|
| author | Meyer, Bertrand |
| author_facet | Meyer, Bertrand |
| contents | Vibe coding, the much-touted use of AI techniques for programming, faces two overwhelming obstacles: the difficulty of specifying goals ("prompt engineering" is a form of requirements engineering, one of the toughest disciplines of software engineering); and the hallucination phenomenon. Programs are only useful if they are correct or very close to correct.
The solution? Combine the creativity of artificial intelligence with the rigor of formal specification methods and the power of formal program verification, supported by modern proof tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_23159 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AI for software engineering: from probable to provable Meyer, Bertrand Software Engineering Artificial Intelligence 68N30, 68T20, 68T05 D.2.4; D.2.2; I.2.2; F.3.1 Vibe coding, the much-touted use of AI techniques for programming, faces two overwhelming obstacles: the difficulty of specifying goals ("prompt engineering" is a form of requirements engineering, one of the toughest disciplines of software engineering); and the hallucination phenomenon. Programs are only useful if they are correct or very close to correct. The solution? Combine the creativity of artificial intelligence with the rigor of formal specification methods and the power of formal program verification, supported by modern proof tools. |
| title | AI for software engineering: from probable to provable |
| topic | Software Engineering Artificial Intelligence 68N30, 68T20, 68T05 D.2.4; D.2.2; I.2.2; F.3.1 |
| url | https://arxiv.org/abs/2511.23159 |