61 citations · 154 across the 41 of their papers we have counts for
45 papers
Regression Accumulation in Multi-Turn LLM Programming Conversations
Yonghui, Huang, Lin Ma +4
In LLM-assisted software development, coding is often iterative. We study regression accumulation in multi-turn LLM programming conversations, where later code suggestions may brea…
From Prompting to Verification: How Experience Shapes Vibe Coding Practices
Ahmed Fawzy, Amjed Tahir, Kelly Blincoe
AI code generation tools have expanded software creation beyond professional developers, giving rise to vibe coding, a practice in which users generate software via natural-languag…
On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies
Ali Soltanian Fard Jahromi, Amjed Tahir, Peng Liang +1
The security of AI-generated code remains a major obstacle to its widespread adoption. Although code generation models achieve strong performance on functional benchmarks, their ou…
Beyond Functional Correctness: Design Issues in AI IDE-Generated Large-Scale Projects
Syed Mohammad Kashif, Ruiyin Li, Peng Liang +4
New generation of AI coding tools, including AI-powered IDEs equipped with agentic capabilities, can generate code within the context of the project. These AI IDEs are increasingly…
The Future of Software Engineering Conferences: A New Zealand Perspective
Kelly Blincoe, Sherlock A. Licorish, Judith Fuchs +1
Software engineering (SE) conferences are vital for knowledge exchange and collaboration, yet can also involve significant barriers for researchers in geographically distant region…
A Systematic Evaluation of Environmental Flakiness in JavaScript Tests
Negar Hashemi, Amjed Tahir, August Shi +2
Test flakiness is a significant issue in industry, affecting test efficiency and product quality. While extensive research has examined the impact of flaky tests, many root causes…
A Survey of Bugs in AI-Generated Code
Ruofan Gao, Amjed Tahir, Peng Liang +2
Developers are widely using AI code-generation models, aiming to increase productivity and efficiency. However, there are also quality concerns regarding the AI-generated code. The…
FasterPy: An LLM-based Code Execution Efficiency Optimization Framework
Yue Wu, Minghao Han, Ruiyin Li +5
Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maint…
Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review
Ahmed Fawzy, Amjed Tahir, Kelly Blincoe
AI code generation tools are transforming software development, especially for novice and non-software developers, by enabling them to write code and build applications faster and…
JS-TOD: Detecting Order-Dependent Flaky Tests in Jest
Negar Hashemi, Amjed Tahir, Shawn Rasheed +2
We present JS-TOD (JavaScript Test Order-dependency Detector), a tool that can extract, reorder, and rerun Jest tests to reveal possible order-dependent test flakiness. Test order…
Decision Models for Selecting Architecture Patterns and Strategies in Quantum Software Systems
Mst Shamima Aktar, Peng Liang, Muhammad Waseem +7
Quantum software is an emerging class of software systems, services, and applications that leverage the principles of quantum mechanics through programmable quantum bits (qubits) a…
On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices
Syed Mohammad Kashif, Peng Liang, Amjed Tahir
AI code generation tools have gained significant popularity among developers, who use them to assist in software development due to their capability to generate code. Existing stud…
Detecting and Evaluating Order-Dependent Flaky Tests in JavaScript
Negar Hashemi, Amjed Tahir, Shawn Rasheed +2
Flaky tests pose a significant issue for software testing. A test with a non-deterministic outcome may undermine the reliability of the testing process, making tests untrustworthy.…
Personalization of Code Readability Evaluation Based on LLM Using Collaborative Filtering
Buntaro Hiraki, Kensei Hamamoto, Ami Kimura +5
Code readability is an important indicator of software maintenance as it can significantly impact maintenance efforts. Recently, LLM (large language models) have been utilized for…
On Applying Bandit Algorithm to Fault Localization Techniques
Masato Nakao, Kensei Hamamoto, Masateru Tsunoda +5
Developers must select a high-performance fault localization (FL) technique from available ones. A conventional approach is to try to select only one FL technique that is expected…
An Empirical Study of the Impact of Test Strategies on Online Optimization for Ensemble-Learning Defect Prediction
Kensei Hamamoto, Masateru Tsunoda, Amjed Tahir +5
Ensemble learning methods have been used to enhance the reliability of defect prediction models. However, there is an inconclusive stability of a single method attaining the highes…
Building Defect Prediction Models by Online Learning Considering Defect Overlooking
Nikolay Fedorov, Yuta Yamasaki, Masateru Tsunoda +5
Building defect prediction models based on online learning can enhance prediction accuracy. It continuously rebuilds a new prediction model, when a new data point is added. However…
The Impact of Defect (Re) Prediction on Software Testing
Yukasa Murakami, Yuta Yamasaki, Masateru Tsunoda +5
Cross-project defect prediction (CPDP) aims to use data from external projects as historical data may not be available from the same project. In CPDP, deciding on a particular hist…
Exploring Data Management Challenges and Solutions in Agile Software Development: A Literature Review and Practitioner Survey
Ahmed Fawzy, Amjed Tahir, Matthias Galster +1
Context: Managing data related to a software product and its development poses significant challenges for software projects and agile development teams. These include integrating d…
An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors
Jiaxin Yu, Peng Liang, Yujia Fu +4
Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security anal…
Selecting Source Code Generation Tools Based on Bandit Algorithms
Ryoto Shima, Masateru Tsunoda, Yukasa Murakami +5
Background: Recently, code generation tools such as ChatGPT have drawn attention to their performance. Generally, a prior analysis of their performance is needed to select new code…
Architecture Decisions in Quantum Software Systems: An Empirical Study on Stack Exchange and GitHub
Mst Shamima Aktar, Peng Liang, Muhammad Waseem +4
Quantum computing provides a new dimension in computation, utilizing the principles of quantum mechanics to potentially solve complex problems that are currently intractable for cl…
Assessing the Security of GitHub Copilot Generated Code -- A Targeted Replication Study
Vahid Majdinasab, Michael Joshua Bishop, Shawn Rasheed +3
AI-powered code generation models have been developing rapidly, allowing developers to expedite code generation and thus improve their productivity. These models are trained on lar…
Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
Yujia Fu, Peng Liang, Amjed Tahir +4
Modern code generation tools utilizing AI models like Large Language Models (LLMs) have gained increased popularity due to their ability to produce functional code. However, their…