Software stakeholders have seamlessly integrated artificial intelligence technologies into the requirements engineering processes for open-source software, which presents both opportunities and challenges. This systematic literature review examines the current state of artificial intelligence application in requirements engineering for open-source software and emphasizes the opportunities and challenges faced by practitioners. Based on the reviewed literature, artificial intelligence technologies, such as machine learning, natural language processing, large language models, and deep learning techniques, have been increasingly applied to support key requirements engineering activities, particularly requirements elicitation, classification, prioritization, and stakeholder analysis. However, the lack of structured data in open-source software directly challenges the effectiveness of artificial intelligence solutions for requirements engineering processes. The findings highlight the need for future research to focus on finding viable solutions to these identified issues. This review provides a consolidated overview for researchers and practitioners interested in enhancing artificial intelligence integration into requirements engineering for open-source software projects and provides guidance for future research to effectively address existing challenges and facilitate integration of AI techniques.
Amal Alharbi, Khaled Slhoub· IEEE Access· 0 citations
Large language models are increasingly deployed on local hardware for privacy, cost, and accessibility reasons. Yet many evaluations emphasize accuracy while fewer quantify local runtime and energy, characterize failure modes, or apply paired statistical comparisons under controlled conditions. This paper presents a controlled, documented procedure for evaluating locally hosted LLMs on mathematical reasoning. It combines fixed inference settings, hierarchical answer extraction and verification, explicit failure-mode classification, and per-question resource measurement, and reports accuracy with paired significance tests and effect sizes. We demonstrate it in a preliminary study of three compact open-weight models under five billion parameters, Gemma3:4b (Google), Phi3:3.8b (Microsoft), and Qwen3:4b (Alibaba), across datasets spanning Grade 8 Math, Calculus I, and Advanced Probability and Statistics. All models ran through the same local inference server on one workstation, using a shared prompt template, controlled settings, and a matched question set per dataset. No single model dominates. Qwen3:4b is most accurate on two datasets and Gemma3:4b on Calculus I, yet Gemma3:4b returns roughly three times more correct answers per watt-hour than Qwen3:4b on every dataset while generating far fewer output tokens; Qwen3:4b requires substantially more generation time, energy, and output per question. Phi3:3.8b is substantially less accurate on all three datasets; its low extraction-failure rate indicates incorrect answers rather than unparsed output, though we caveat possible prompt-format effects. These preliminary findings indicate that accuracy alone is an insufficient basis for selecting a local model.
Test Case Prioritization (TCP) aims to reorder test cases to enable earlier fault detection in Continuous Integration pipelines. Machine learning-based TCP approaches have shown promising results but require substantial historical execution data, creating a cold-start challenge for new or rapidly evolving projects. This paper presents an empirical study of direct transfer learning, where models trained on data-rich source projects are applied to unseen targets without any retraining. A total of 578 experiments are conducted across 17 Defects4J projects (34 within-project baselines and 544 cross-project transfer scenarios) using 270,611 feature vectors. Results show that with appropriate source selection, cross-project transfer can match or surpass within-project baselines. A three-way feature ablation (HIS-only, COV-only, full 13-feature) finds that no feature subset consistently exceeds random ordering (E[APFD]≈0.5) on average, confirming that source selection is the critical variable. Analysis identifies failure-rate alignment and source dataset richness as key predictors of transfer quality, providing source-selection criteria that require no target-side data collection.
Michael Johnson, Khaled Slhoub· International Conference on...· 0 citations