Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Alberta

$42,000.00

The automation of software engineering processes

FY 2024-25

Summary
This proposal requests funding for ongoing research in automating Software Engineering (SE) activities using Artificial Intelligence (AI), particularly unsupervised representation and language models. During the past six years, my research group showed exceptional progress in various topics spanning SE and AI. In SE, successful software testing and Lean engineering projects were conducted. Within AI, research achievements revolved around dimensionality reduction strategies, including a notable thesis that won the best thesis award in the department. The research also investigated weak supervision and large language models (LLMs). Underserved representation was applied to model attribute dependencies in tabular data, leading to a patented solution for finding erroneous data cells in databases. This work has resulted in five completed Ph.D. dissertations, seven MSc theses, and 30 journal publications published in the last six years. Building on this progress, this research proposal aims to harness the potential of Generative AI, particularly LLMs, to revolutionize the field of Software Engineering. LLMs can significantly enhance productivity, with the potential to boost software engineering efficiency by up to 45 percent annually. However, deploying AI in software engineering has its challenges. Issues surrounding data quality and computational resources remain areas of concern. Therefore, this research project sets forth two primary objectives. The first objective delves into the automation of SE activities through AI, focusing on integrating LLMs into multiagent systems. This integration is poised to enhance efficiency by capitalizing on the strengths of both models, thereby enabling automated requirement engineering, system design, quality assurance, and program repair activities. The second objective centers on the critical task of selecting and preprocessing the right training datasets for language models tailored to software engineering tasks. Addressing these challenges is essential to ensure the suitability and cleanliness of training data. By automating these steps, the research aims to mitigate model misbehavior and reduce training costs, ultimately advancing the field of AI in Software Engineering. By addressing these objectives, this research seeks to pave the way for the effective utilization of AI, LLMs, and multiagent systems in software engineering while tackling key data quality and preprocessing challenges. This comprehensive approach aims to unlock the full potential of AI in reshaping software development practices, making them more efficient and productive. The proposed research aims to offer novel perspectives into these two objectives and produce AI systems that enhance the automation of software engineering activities. In our plan, 3 Ph.D. students will work on building AI models to automate different software engineering activities, while one Ph.D. student focus on investigating the data quality and preprocessing issues.
Program
Discovery Grants Program - Individual
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-04575
Name nom
Miller, James
Department département
Electrical and Computer Eng.
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
42000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
800
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information and communication services
Area of application fr
Services d'information et de télécommunications
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
The automation of software engineering processes
Keywords
software engineering; automation; software development; artificial intelligence
Application summary
This proposal requests funding for ongoing research in automating Software Engineering (SE) activities using Artificial Intelligence (AI), particularly unsupervised representation and language models. During the past six years, my research group showed exceptional progress in various topics spanning SE and AI. In SE, successful software testing and Lean engineering projects were conducted. Within AI, research achievements revolved around dimensionality reduction strategies, including a notable thesis that won the best thesis award in the department. The research also investigated weak supervision and large language models (LLMs). Underserved representation was applied to model attribute dependencies in tabular data, leading to a patented solution for finding erroneous data cells in databases. This work has resulted in five completed Ph.D. dissertations, seven MSc theses, and 30 journal publications published in the last six years. Building on this progress, this research proposal aims to harness the potential of Generative AI, particularly LLMs, to revolutionize the field of Software Engineering. LLMs can significantly enhance productivity, with the potential to boost software engineering efficiency by up to 45 percent annually. However, deploying AI in software engineering has its challenges. Issues surrounding data quality and computational resources remain areas of concern. Therefore, this research project sets forth two primary objectives. The first objective delves into the automation of SE activities through AI, focusing on integrating LLMs into multiagent systems. This integration is poised to enhance efficiency by capitalizing on the strengths of both models, thereby enabling automated requirement engineering, system design, quality assurance, and program repair activities. The second objective centers on the critical task of selecting and preprocessing the right training datasets for language models tailored to software engineering tasks. Addressing these challenges is essential to ensure the suitability and cleanliness of training data. By automating these steps, the research aims to mitigate model misbehavior and reduce training costs, ultimately advancing the field of AI in Software Engineering. By addressing these objectives, this research seeks to pave the way for the effective utilization of AI, LLMs, and multiagent systems in software engineering while tackling key data quality and preprocessing challenges. This comprehensive approach aims to unlock the full potential of AI in reshaping software development practices, making them more efficient and productive. The proposed research aims to offer novel perspectives into these two objectives and produce AI systems that enhance the automation of software engineering activities. In our plan, 3 Ph.D. students will work on building AI models to automate different software engineering activities, while one Ph.D. student focus on investigating the data quality and preprocessing issues.