7 papers
CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
Yifei Wang, Ruiyin Li, Peng Liang +4
Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with functi…
Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
Guangzong Cai, Ruiyin Li, Peng Liang +2
The adoption of AI-powered Integrated Development Environments (AI IDEs) has introduced "Rules" as a novel software artifact, allowing developers to persistently inject project-spe…
Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey
Yifei Wang, Ruiyin Li, Peng Liang +5
Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, including software design, an area tr…
ArchISMiner: A Framework for Automatic Mining of Architectural Issue-Solution Pairs from Online Developer Communities
Musengamana Jean de Dieu, Ruiyin Li, Peng Liang +5
Stack Overflow (SO), a leading online community forum, is a rich source of software development knowledge. However, locating architectural knowledge, such as architectural solution…
How Do Users Revise Architectural Related Questions on Stack Overflow: An Empirical Study
Musengamana Jean de Dieu, Peng Liang, Mojtaba Shahin +1
Technical Questions and Answers (Q&A) sites, such as Stack Overflow (SO), accumulate a significant variety of information related to software development in posts from users. To en…
How Do OSS Developers Reuse Architectural Solutions from Q&A Sites: An Empirical Study
Musengamana Jean de Dieu, Peng Liang, Mojtaba Shahin
Developers reuse programming-related knowledge on Q&A sites that functionally matches the programming problems they encounter in their development. Despite extensive research on Q&…