9 papers
Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications
Nasser Giacaman, Valerio Terragni, Paul Denny +1
As AI code tools become integrated into programming environments, students increasingly describe intended behavior in natural language and rely on these tools to generate code, shi…
An Evaluation of Role-Based Multi-Agent Code Generation on Repository-Scale Problems
Benedetta Donato, Noah Hagar-Dent, Aaron Worsnop +2
Role-based multiagent code generation aims to make LLMs more effective on repository-scale problems, moving beyond small programming tasks. We evaluate this approach on 12 Java rep…
MR-Adopt: Automatic Deduction of Input Transformation Function for Metamorphic Testing
Congying Xu, Songqiang Chen, Jiarong Wu +4
While a recent study reveals that many developer-written test cases can encode a reusable Metamorphic Relation (MR), over 70% of them directly hard-code the source input and follow…
MR-Scout: Automated Synthesis of Metamorphic Relations from Existing Test Cases
Congying Xu, Valerio Terragni, Hengcheng Zhu +2
Metamorphic Testing (MT) alleviates the oracle problem by defining oracles based on metamorphic relations (MRs), that govern multiple related inputs and their outputs. However, des…
The Future of AI-Driven Software Engineering
Valerio Terragni, Annie Vella, Partha Roop +1
A paradigm shift is underway in Software Engineering, with AI systems such as LLMs playing an increasingly important role in boosting software development productivity. This trend…
Adoption and Evolution of Code Style and Best Programming Practices in Open-Source Projects
Alvari Kupari, Nasser Giacaman, Valerio Terragni
Following code style conventions in software projects is essential for maintaining overall code quality. Adhering to these conventions improves maintainability, understandability,…