9 papers
Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report
Mariama Celi Serafim De Oliveira, Motunrayo Osatohanmen Ibiyo, Marco Gianrusso +3
The proliferation of Generative Artificial Intelligence (Gen AI) powered by large language models (LLMs) has transformed the software development process, introducing new paradigms…
TerraRepair: A Tool-Grounded LLM Agent for Infrastructure-as-Code Repair
Minase Mekete Mengistu, Juri Di Rocco, Phuong T. Nguyen +1
Background: Infrastructure-as-Code (IaC) scanners detect cloud misconfigurations in Terraform and other IaC languages before deployment, but repairing the flagged configurations re…
The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG Systems
Abu Saleh, Tesfay Welegebreal Tesfay, Phuong T. Nguyen +3
Large Language Models (LLMs) are increasingly utilized to automate several software engineering tasks, including code completion, code summarization, testing, and the generation of…
Generate with CodeXHug: A Dataset to Enhance Model Cards with Code Usage Patterns
Stefano Palombo, Claudio Di Sipio, Juri Di Rocco +1
Pre-trained models (PTMs) are becoming increasingly popular in the software engineering community. Their usage is facilitated by model repositories, e.g., HuggingFace, which collec…
Automatic Categorization of GitHub Actions with Transformers and Few-shot Learning
Phuong T. Nguyen, Juri Di Rocco, Claudio Di Sipio +3
In the GitHub ecosystem, workflows are used as an effective means to automate development tasks and to set up a Continuous Integration and Delivery (CI/CD pipeline). GitHub Actions…
Good things come in three: Generating SO Post Titles with Pre-Trained Models, Self Improvement and Post Ranking
Duc Anh Le, Anh M. T. Bui, Phuong T. Nguyen +1
Stack Overflow is a prominent Q and A forum, supporting developers in seeking suitable resources on programming-related matters. Having high-quality question titles is an effective…