Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable Code
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41096-41097
DOI: 10.1609/aaai.v40i48.42174 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jian Wang.
Abstract (Originalsprache)
The widespread adoption of AI-assisted coding tools has fundamentally transformed software development, enabling rapid code generation but simultaneously introducing new risks to software reliability. This thesis addresses the critical challenge of ensuring trustworthy AI-assisted programming through two complementary approaches: detecting AI-generated code and advancing automated program repair. I present four major contributions: (1) The first comprehensive empirical study of AI-generated code detection across 2.24 million samples with fine-tuning-based improvements, (2) Defects4C, the first large-scale executable C/C++ bug benchmark with 248 real-world bugs, (3) Novel automated repair methods combining deep learning and LLM-based approaches with extensive empirical evaluation, and (4) A semantic enhancement framework that incorporates execution traces to improve LLM reasoning for program repair. These contributions establish new foundations for trustworthy, semantically grounded automated program repair in the era of AI-assisted development.
Zitieren
APA
Wang, J. (2026). Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable Code. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41096-41097. https://doi.org/10.1609/aaai.v40i48.42174
Vancouver
Wang J. Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable Code. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41096-41097. doi:10.1609/aaai.v40i48.42174
BibTeX
@article{Wang2026,
author = {Wang, Jian},
title = {Trustworthy AI-Assisted Programming: Detection and Repair of Unreliable Code},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41096--41097},
doi = {10.1609/aaai.v40i48.42174}
}
EUVIMED