Abstract

Abstract

Abstract
ABSTRACTContextGenerative artificial intelligence (GenAI) tools have become increasingly prevalent in software development, offering assistance to various managerial and technical project activities. Notable examples of these tools include OpenAI's ChatGPT, GitHub Copilot, and Amazon CodeWhisperer.ObjectiveAlthough many recent publications have explored and evaluated the application of GenAI, a comprehensive understanding of the current development, applications, limitations, and open challenges remains unclear to many. Particularly, we do not have an overall picture of the current state of GenAI technology in practical software engineering usage scenarios.MethodWe conducted a literature review and focus groups for a duration of five months to develop a research agenda on GenAI for software engineering.ResultsWe identified 78 open research questions (RQs) in 11 areas of software engineering. Our results show that it is possible to explore the adoption of GenAI in partial automation and support decision-making in all software development activities. While the current literature is skewed toward software implementation, quality assurance and software maintenance, other areas, such as requirements engineering, software design, and software engineering education, would need further research attention. Common considerations when implementing GenAI include industry-level assessment, dependability and accuracy, data accessibility, transparency, and sustainability aspects associated with the technology.ConclusionsGenAI is bringing significant changes to the field of software engineering. Nevertheless, the state of research on the topic still remains immature. We believe that this research agenda holds significance and practical value for informing both researchers and practitioners about current applications and guiding future research.

Abstract
Text-to-SQL has gained increasing attention with Large Language Models (LLMs). While existing architectures have demonstrated the potential of multi-agent systems there remains significant room for improvement. In this work, we extend the CHESS framework by integrating In-Context Learning (ICL) techniques into the Candidate Generator module, evaluating three strategies: Zero-Shot, Few-Shot Learning, and Retrieval-Augmented Generation (RAG). We implement the system using GPT-4o, and perform experiments on the financial dataset from BIRD-SQL. Results show that Few-Shot Learning and RAG significantly outperform the standard approach. Compared to Zero-Shot (59.31% Execution Accuracy (EX), 0.412 ROUGE-1), RAG significantly boosted performance, increasing EX to 69.48% and ROUGE-1 to 0.652.

Abstract
Introduction: This work explores the challenges faced by students with disabilities in higher education; focusing on the accessibility of digital learning resources provided through Learning Management Systems (LMS). While inclusive education is a growing priority; many institutions still fall short of fully meeting accessibility standards. This lack of accessibility limits the participation and academic success of students with disabilities. Objective: This work aims to develop tools to help educators evaluate and improve the accessibility of content within LMS. Methodology: To support this goal; the project includes the development of a real-time accessibility dashboard; providing institutions with a centralized platform to monitor and address accessibility issues across their digital learning environments. Expected Results: By implementing these solutions; the project seeks to promote educational inclusion and enhance the academic success of students with disabilities.

Abstract
Introduction: Surveys are a key method for collecting data, used in contexts ranging from national censuses to customer satisfaction assessments. Despite their clear utility, recent literature highlights their inaccessibility to people with disabilities. Objective: This paper outlines the development of a survey completion tool accessible to people with disabilities. Methodology: Key steps included identifying requirements for designing an accessible survey completion tool, implementing them, testing the tool with people with disabilities, and refning it based on identifed issues and suggested changes. Results: Overall, the tool was found to be accessible to people with diverse disabilities.