arXiv subjects

Vincenzo De Martino

Publications and source records attributed to Vincenzo De Martino.

9 recordsLinked to original sources

arXiv2026

From Prompting to Engineering: A Research Agenda for Prompt Engineering in Software Engineering

Prompt engineering is increasingly used across Software Engineering (SE) activities, including requirements analysis, coding, testing, documentation, repository analysis, and planning. Yet prompts and related instruction artifacts are often created and evolved through task-specific and informal practices, with limited support for their systematic evaluation, management, traceability, and governance. To examine how SE can contribute to the maturation of these practices, we organized a structured community discussion at the First International Workshop on Empirical Prompt Engineering for Software Engineering (PROMPT-SE), co-located with EASE 2026. Participants discussed current prompting practices, challenges to their adoption and evaluation, and future directions for integrating prompt engineering into software development. We synthesized these discussions into five areas: prompt artifacts and standardization; evaluation and benchmarking; lifecycle integration; human-AI collaboration and skills; and governance, privacy, and technical debt. Based on these areas, we outline a research agenda to move prompt engineering from predominantly ad hoc interactions toward more systematic, maintainable, evaluable, traceable, and governable SE practices.

cs.SE↗

arXiv2026

Green Architectural Tactics in ML-enabled Systems: An LLM-based Repository Mining Study

Context: The increasing adoption of machine learning (ML) and artificial intelligence (AI) technologies raises growing concerns about their environmental sustainability. Developing and deploying ML-enabled systems is computationally intensive, particularly during training and inference. Green AI has emerged to address these issues by promoting efficiency without sacrificing accuracy. While prior research has proposed catalogs of sustainable practices (i.e., green tactics), there remains limited understanding of their adoption in practice and whether additional, undocumented tactics exist. Objective: This study aims to investigate the extent to which existing sustainable practices are implemented in real-world ML-enabled systems and to identify previously undocumented practices that support environmental sustainability. Method: We conduct a mining software repository study on 205 open-source ML projects on GitHub. To support our analysis, we design a novel mechanism based on large language models (LLMs) capable of identifying both known and new sustainable practices from code repositories. Results: Our findings confirm that green tactics reported in the literature are used in practice, although adoption rates vary. Furthermore, our LLM-based approach reveals nine previously undocumented sustainable practices. Each tactic is supported with code examples to aid adoption and integration. Conclusions: We finally provide insights for practitioners seeking to reduce the environmental impact of ML-enabled systems and offer a foundation for future research in automating the detection and adoption of sustainable practices.

cs.SE↗

arXiv2025

Sustainability of Machine Learning-Enabled Systems: The Machine Learning Practitioner's Perspective

Software sustainability is a key multifaceted non-functional requirement that encompasses environmental, social, and economic concerns, yet its integration into the development of Machine Learning (ML)-enabled systems remains an open challenge. While previous research has explored high-level sustainability principles and policy recommendations, limited empirical evidence exists on how sustainability is practically managed in ML workflows. Existing studies predominantly focus on environmental sustainability, e.g., carbon footprint reduction, while missing the broader spectrum of sustainability dimensions and the challenges practitioners face in real-world settings. To address this gap, we conduct an empirical study to characterize sustainability in ML-enabled systems from a practitioner's perspective. We investigate (1) how ML engineers perceive and describe sustainability, (2) the software engineering practices they adopt to support it, and (3) the key challenges hindering its adoption. We first perform a qualitative analysis based on interviews with eight experienced ML engineers, followed by a large-scale quantitative survey with 203 ML practitioners. Our key findings reveal a significant disconnection between sustainability awareness and its systematic implementation, highlighting the need for more structured guidelines, measurement frameworks, and regulatory support.

cs.SE↗

arXiv2025

Does Model Size Matter? A Comparison of Small and Large Language Models for Requirements Classification

[Context and motivation] Large language models (LLMs) show notable results in natural language processing (NLP) tasks for requirements engineering (RE). However, their use is compromised by high computational cost, data sharing risks, and dependence on external services. In contrast, small language models (SLMs) offer a lightweight, locally deployable alternative. [Question/problem] It remains unclear how well SLMs perform compared to LLMs in RE tasks in terms of accuracy. [Results] Our preliminary study compares eight models, including three LLMs and five SLMs, on requirements classification tasks using the PROMISE, PROMISE Reclass, and SecReq datasets. Our results show that although LLMs achieve an average F1 score of 2% higher than SLMs, this difference is not statistically significant. SLMs almost reach LLMs performance across all datasets and even outperform them in recall on the PROMISE Reclass dataset, despite being up to 300 times smaller. We also found that dataset characteristics play a more significant role in performance than model size. [Contribution] Our study contributes with evidence that SLMs are a valid alternative to LLMs for requirements classification, offering advantages in privacy, cost, and local deployability.

cs.SE↗

arXiv2025

A First Look at the Lifecycle of DL-Specific Self-Admitted Technical Debt

The rapid adoption of Deep Learning (DL)-enabled systems has revolutionized software development, driving innovation across various domains. However, these systems also introduce unique challenges, particularly in maintaining software quality and performance. Among these challenges, Self-Admitted Technical Debt (SATD) has emerged as a growing concern, significantly impacting the maintainability and overall quality of ML and DL-enabled systems. Despite its critical implications, the lifecycle of DL-specific SATD, how developers introduce, acknowledge, and address it over time-remains underexplored. This study presents a preliminary analysis of the persistence and lifecycle of DL-specific SATD in DL-enabled systems. The purpose of this project is to uncover the patterns of SATD introduction, recognition, and durability during the development life cycle, providing information on how to manage these issues. Using mining software repository techniques, we examined 40 ML projects, focusing on 185 DL-specific SATD instances. The analysis tracked the introduction and persistence of SATD instances through project commit histories to assess their lifecycle and developer actions. The findings indicate that DL-specific SATD is predominantly introduced during the early and middle stages of project development. Training and Hardware phases showed the longest SATD durations, highlighting critical areas where debt accumulates and persists. Additionally, developers introduce DL-specific SATD more frequently during feature implementation and bug fixes. This study emphasizes the need for targeted DL-specific SATD management strategies in DL-enabled systems to mitigate its impact. By understanding the temporal characteristics and evolution of DL-specific SATD, developers can prioritize interventions at critical stages to improve the maintainability and quality of the system.

cs.SE↗

arXiv2025

Green Prompt Engineering: Investigating the Energy Impact of Prompt Design in Software Engineering

Language Models are increasingly applied in software engineering, yet their inference raises growing environmental concerns. Prior work has examined hardware choices and prompt length, but little attention has been paid to linguistic complexity as a sustainability factor. This paper introduces Green Prompt Engineering, framing linguistic complexity as a design dimension that can influence energy consumption and performance. We conduct an empirical study on requirement classification using open-source Small Language Models, varying the readability of prompts. Our results reveal that readability affects environmental sustainability and performance, exposing trade-offs between them. For practitioners, simpler prompts can reduce energy costs without a significant F1-score loss; for researchers, it opens a path toward guidelines and studies on sustainable prompt design within the Green AI agenda.

cs.SE↗

arXiv2025

A Methodological Framework for LLM-Based Mining of Software Repositories

Large Language Models (LLMs) are increasingly used in software engineering research, offering new opportunities for automating repository mining tasks. However, despite their growing popularity, the methodological integration of LLMs into Mining Software Repositories (MSR) remains poorly understood. Existing studies tend to focus on specific capabilities or performance benchmarks, providing limited insight into how researchers utilize LLMs across the full research pipeline. To address this gap, we conduct a mixed-method study that combines a rapid review and questionnaire survey in the field of LLM4MSR. We investigate (1) the approaches and (2) the threats that affect the empirical rigor of researchers involved in this field. Our findings reveal 15 methodological approaches, nine main threats, and 25 mitigation strategies. Building on these findings, we present PRIMES 2.0, a refined empirical framework organized into six stages, comprising 23 methodological substeps, each mapped to specific threats and corresponding mitigation strategies, providing prescriptive and adaptive support throughout the lifecycle of LLM-based MSR studies. Our work contributes to establishing a more transparent and reproducible foundation for LLM-based MSR research.

cs.SE↗

arXiv2025

Do Developers Adopt Green Architectural Tactics for ML-Enabled Systems? A Mining Software Repository Study

As machine learning (ML) and artificial intelligence (AI) technologies become more widespread, concerns about their environmental impact are increasing due to the resource-intensive nature of training and inference processes. Green AI advocates for reducing computational demands while still maintaining accuracy. Although various strategies for creating sustainable ML systems have been identified, their real-world implementation is still underexplored. This paper addresses this gap by studying 168 open-source ML projects on GitHub. It employs a novel large language model (LLM)-based mining mechanism to identify and analyze green strategies. The findings reveal the adoption of established tactics that offer significant environmental benefits. This provides practical insights for developers and paves the way for future automation of sustainable practices in ML systems.

cs.SE↗

arXiv2024

Classification, Challenges, and Automated Approaches to Handle Non-Functional Requirements in ML-Enabled Systems: A Systematic Literature Review

Context: Machine learning (ML) is nowadays so pervasive and diffused that virtually no application can avoid its use. Nonetheless, its enormous potential is often tempered by the need to manage non-functional requirements and navigate pressing, contrasting trade-offs. Objective: In this respect, we notice the lack of a comprehensive synthesis of the non-functional requirements affecting ML-enabled systems, other than the major challenges faced to deal with them. Such a synthesis may not only provide a comprehensive summary of the state of the art, but also drive further research on the analysis, management, and optimization of non-functional requirements of ML-intensive systems. Method: In this paper, we propose a systematic literature review targeting two key aspects such as (1) the classification of the non-functional requirements investigated so far, and (2) the challenges to be faced when developing models in ML-enabled systems. Through the combination of well-established guidelines for conducting systematic literature reviews and additional search criteria, we survey a total amount of 69 research articles. Results: Our findings report that current research identified 30 different non-functional requirements, which can be grouped into six main classes. We also compiled a catalog of more than 23 software engineering challenges, based on which further research should consider the nonfunctional requirements of machine learning-enabled systems. Conclusion: We conclude our work by distilling implications and a future outlook on the topic.

cs.SE↗