Andrea De Lucia

Quantum computing is steadily transitioning from theoretical exploration to experimental deployment, bringing with it distinct engineering challenges. This shift has led to the emergence of Quantum Software Engineering (QSE), a research area that adapts and extends software engineering principles to the quantum domain. In parallel, Large Language Models (LLMs) have become widely adopted in classical software development workflows. Although their potential to assist QSE tasks is increasingly discussed, existing evidence remains fragmented across research venues and practitioner sources. This study presents a Multivocal Literature Review that systematically synthesizes peer-reviewed and grey literature to characterize how LLMs are used in QSE and assess their reported limitations. We identified and analyzed 24 primary sources, mapped their contributions onto the quantum software development lifecycle, examined the distribution of adopted LLM families, and synthesized recurring limitations. The results show that LLM adoption in QSE is predominantly code-centric, with most studies focusing on program synthesis, repair, and refactoring, while lifecycle phases such as requirements engineering, architectural reasoning, and comprehensive validation receive limited attention. Reported challenges include semantic inaccuracies, execution failures on real quantum backends, sensitivity to prompt formulation, and limited domain coverage. Moreover, the empirical landscape is largely shaped by proprietary models, raising concerns regarding reproducibility and longitudinal comparability. Overall, current evidence suggests that LLMs function primarily as assistive tools for bounded tasks rather than as robust, lifecycle-spanning engineering agents in quantum software development.

Context: Quantum software technologies (QSTs) are emerging as a promising field, offering developers powerful tools to push the boundaries of software innovation. However, a technology that is not adopted remains nothing more than an untapped potential. Despite increasing interest in integrating quantum computing into software development, significant barriers still hinder its widespread adoption. While much of the existing research has focused on technical advancements, the socio-technical factors influencing adoption have been largely overlooked. Understanding these factors could provide managers and engineers with actionable insights to facilitate adoption, as developers’ perceptions and attitudes can be shaped and managed more readily than technological advancements. Objective: This study addresses this gap by statistically analyzing the determinants of QST adoption among software professionals. Method: Leveraging established adoption theories (UTAUT2 and Diffusion of Innovation) and incorporating perceived trust, data were collected using validated questionnaires and analyzed with Partial Least Squares Structural Equation Modeling (PLS-SEM). Results: Findings indicate that compatibility, personal innovativeness, and performance expectancy are key drivers of adoption, while financial concerns negatively influence it. Moreover, workplace support and habitual exposure emerged as critical enablers of actual usage, emphasizing the importance of organizational interventions. Conclusions: These insights offer practical guidance for companies developing and maintaining QSTs into their workflows while identifying new research directions, including barriers to adoption, long-term engagement, and financial considerations.

Context : Vulnerability-contributing commits (VCCs) are code changes that introduce vulnerabilities. Mining historical VCCs relies on SZZ-based algorithms that trace from known vulnerability-fixing commits. Objective : Although these techniques have been used, e.g., to train just-in-time vulnerability predictors, they lack systematic benchmarking to evaluate their precision, recall, and error sources. Method : We empirically assessed 12 VCC mining techniques in Java repositories using two benchmark datasets (one from the literature and one newly curated). We also explored combinations of techniques, through intersections, voting schemes, and machine learning, to improve performance. Results : Individual techniques achieved at most 0.60 precision but up to 0.89 recall. The precision rose to 0.75 when the outputs were combined with the logical AND, at the expense of recall. Machine learning ensembles reached 0.80 precision with a better precision–recall balance. Performance varied significantly by dataset. Analyzing “fixing commits” showed that certain fix types (e.g., filtering or sanitization) affect retrieval accuracy, and failure patterns highlighted weaknesses when fixes involve external data handling. Conclusion : Such results help software security researchers select the most suitable mining technique for their studies and understand new ways to design more accurate solutions.

Successful software development hinges on effective communication and collaboration, which are significantly influenced by human and social dynamics. Poor management of these elements can lead to the emergence of ‘community smells’, i.e., negative patterns in socio-technical interactions that gradually accumulate as ‘social debt’. This issue is particularly pertinent in machine learning-enabled systems, where diverse actors such as data engineers and software engineers interact at various levels. The unique collaboration context of these systems presents an ideal setting to investigate community smells and their impact on development communities. This article addresses a gap in the literature by identifying the types, causes, effects, and potential mitigation strategies of community smells in machine learning-enabled systems. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), we developed hypotheses based on existing literature and interviews, and conducted a questionnaire-based study to collect data. Our analysis resulted in the construction and validation of five models that represent the causes, effects, and strategies for five specific community smells. These models can help practitioners identify and address community smells within their organizations, while also providing valuable insights for future research on the socio-technical aspects of machine learning-enabled system communities.