AI-Driven Augmented Software Engineering: Leveraging Cognitive Models for Enhanced Code Generation

Ameen Shaheen; Mohammad Al Khaldy; Wael Alzyadat; Aysh Alhroob

doi:10.47852/bonviewJCCE52026123

Authors

Ameen Shaheen Department of Software Engineering, Al-Zaytoonah University of Jordan, Jordan https://orcid.org/0009-0003-3120-1892
Mohammad Al Khaldy Department of Business Intelligence and Data Analytics, University of Petra, Jordan https://orcid.org/0009-0009-7502-4668
Wael Alzyadat Department of Software Engineering, Al-Zaytoonah University of Jordan, Jordan https://orcid.org/0000-0002-0068-1526
Aysh Alhroob Department of Software Engineering, Al-Zaytoonah University of Jordan, Jordan https://orcid.org/0000-0002-4653-7386

DOI:

https://doi.org/10.47852/bonviewJCCE52026123

Keywords:

AI-driven, code generation, cognitive models, developer productivity, software engineering, development automation

Abstract

Artificial intelligence (AI) is transforming the software engineering landscape that allows for new development approaches. This paper proposes a framework that integrates cognitive models with AI-driven code generation to enhance the software development process. By leveraging cognitive principles, the proposed system performs human-like decision-making to optimize code generation, refactor existing code, and fix bugs. The framework was evaluated based on code quality, developer productivity, usability, and system adaptability. Results demonstrate improvements by AI-driven system such as speed of code generation increased by 10% compared with human-written baseline and complexity reduced by 15% compared with human-generated code. Developers using the system reported a 25–29% reduction in task completion time, and errors were minimized by 60–67%. Usability feedback indicated that the system integrated seamlessly into developers’ workflows but requires further development, including enhanced personalization and a better understanding of complex code contexts. This study highlights the potential of AI-driven systems to assist developers in producing high-quality software more efficiently and provides a foundation for future research in AI-enhanced software engineering tools.

Received: 10 May 2025 | Revised: 24 September 2025 | Accepted: 11 October 2025

Conflicts of Interest

The authors declare that they have no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available in the CodeSearchNet repository at https://github.com/github/CodeSearchNet.

Author Contribution Statement

Ameen Shaheen: Conceptualization, Software, Writing – original draft, Visualization. Mohammad Al Khaldy: Methodology, Writing – review & editing, Supervision, Project administration. Wael Alzyadat: Validation, Formal analysis, Resources, Writing – review & editing. Aysh Alhroob: Investigation, Data curation, Writing – review & editing.