arXiv subjects

Andrea De Lucia

Publications and source records attributed to Andrea De Lucia.

13 recordsLinked to original sources

arXiv2026

How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study

Context. Autonomous coding agents are increasingly used in software development, shifting parts of the engineering process to AI assistance. While this automation brings clear benefits, it introduces challenges in governance, traceability, and control over agent behavior. Agent Context Files (ACFs) have emerged as a practical mechanism to guide agents through structured instructions, yet little is known about how these artifacts are maintained and how their evolution relates to code development. Objective. This paper plans to investigate the evolution of ACFs and their role in agent-driven development. Specifically, we (1) classify ACF changes through a taxonomy grounded in software maintenance theory, (2) analyze how different types of changes are associated with code quality outcomes, and (3) examine their temporal patterns across the development lifecycle. Method. We conduct a large-scale mining study combining repositories with ACFs and agent-generated commits. We reconstruct ACF evolution at the commit level, classify changes using a qualitative approach, and analyze their association with code quality metrics. Statistical analyses and hypotheses are used to evaluate differences across maintenance categories, to inform future design of ACFs for governing autonomous coding agents.

cs.SE↗

arXiv2026

SCOPE: A Dataset of Stereotyped Prompts for Counterfactual Fairness Assessment of LLMs

Large Language Models (LLMs) now serve as the foundation for a wide range of applications, from conversational assistants to decision support tools, making the issue of fairness in their results increasingly important. Previous studies have shown that LLM outputs can shift when prompts reference different demographic groups, even when intent and semantic content remain constant. However, existing resources for probing such disparities rely primarily on small, template-based counterfactual examples or fixed sentence pairs. These benchmarks offer limited linguistic diversity, narrow topical coverage, and little support for analyzing how communicative intent affects model behavior. To address these limitations, we introduce SCOPE (Stereotype-COnditioned Prompts for Evaluation), a large-scale dataset of counterfactual prompt pairs designed to enable systematic investigation of group-sensitive behavior in LLMs. SCOPE contains 241,280 prompts organized into 120,640 counterfactual pairs, each grounded in one of 1,438 topics and spanning nine bias dimensions and 1,536 demographic groups. All prompts are generated under four distinct communicative intents: Question, Recommendation, Direction, and Clarification, ensuring broad coverage of common interaction styles. This resource provides a controlled, semantically aligned, and intent-aware basis for evaluating fairness, robustness, and counterfactual consistency.

cs.SE↗

arXiv2026

Bias Ahead: Sensitive Prompts as Early Warnings for Fairness in Large Language Models

Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations, which limit their ability to anticipate risks in diverse, real-world contexts. In this paper, we propose sensitive prompts as a new abstraction for fairness evaluation: inputs that are not inherently biased but are more likely to elicit biased or inadequate responses due to the sensitivity of their content. We construct and release SensY, a dataset of 12,801 prompts, categorized as sensitive and non-sensitive, spanning seven thematic domains, combining synthetic generation and real user inputs. Using this dataset, we query three open-source LLMs and manually analyze 4,500 responses to evaluate their adequacy in answering sensitive prompts. Results show that while models often provide factually correct answers, they frequently fail to acknowledge the ethical, relational, or contextual implications of sensitive inputs. In addition, we develop an automated classifier for predicting prompt sensitivity, achieving robust performance on sensitive prompts. Our findings demonstrate that prompt sensitivity can serve as an effective early-warning mechanism for fairness risks in LLMs. This perspective shifts fairness assessment from reactive mitigation toward preventive design, enabling developers to anticipate and manage bias before deployment.

cs.SE↗

arXiv2026

Socio-Technical Well-Being of Quantum Software Communities: An Overview on Community Smells

Quantum computing has gained significant attention due to its potential to solve computational problems beyond the capabilities of classical computers. With major corporations and academic institutions investing in quantum hardware and software, there has been a rise in the development of quantum-enabled systems, particularly within open-source communities. However, despite the promising nature of quantum technologies, these communities face critical socio-technical challenges, including the emergence of socio-technical anti-patterns known as community smells. These anti-patterns, prevalent in open-source environments, have the potential to negatively impact both product quality and community health by introducing technical debt and amplifying architectural and code smells. Despite the importance of these socio-technical factors, there remains a scarcity of research investigating their influence within quantum open-source communities. This work aims to address this gap by providing a first step in analyzing the socio-technical well-being of quantum communities through a cross-sectional study. By understanding the socio-technical dynamics at play, it is expected that foundational knowledge can be established to mitigate the risks associated with community smells and ensure the long-term sustainability of open-source quantum initiatives.

cs.SE↗

arXiv2025

Toward Systematic Counterfactual Fairness Evaluation of Large Language Models: The CAFFE Framework

Nowadays, Large Language Models (LLMs) are foundational components of modern software systems. As their influence grows, concerns about fairness have become increasingly pressing. Prior work has proposed metamorphic testing to detect fairness issues, applying input transformations to uncover inconsistencies in model behavior. This paper introduces an alternative perspective for testing counterfactual fairness in LLMs, proposing a structured and intent-aware framework coined CAFFE (Counterfactual Assessment Framework for Fairness Evaluation). Inspired by traditional non-functional testing, CAFFE (1) formalizes LLM-Fairness test cases through explicitly defined components, including prompt intent, conversational context, input variants, expected fairness thresholds, and test environment configuration, (2) assists testers by automatically generating targeted test data, and (3) evaluates model responses using semantic similarity metrics. Our experiments, conducted on three different architectural families of LLM, demonstrate that CAFFE achieves broader bias coverage and more reliable detection of unfair behavior than existing metamorphic approaches.

cs.SE↗

arXiv2025

A Catalog of Fairness-Aware Practices in Machine Learning Engineering

Machine learning's widespread adoption in decision-making processes raises concerns about fairness, particularly regarding the treatment of sensitive features and potential discrimination against minorities. The software engineering community has responded by developing fairness-oriented metrics, empirical studies, and approaches. However, there remains a gap in understanding and categorizing practices for engineering fairness throughout the machine learning lifecycle. This paper presents a novel catalog of practices for addressing fairness in machine learning derived from a systematic mapping study. The study identifies and categorizes 28 practices from existing literature, mapping them onto different stages of the machine learning lifecycle. From this catalog, the authors extract actionable items and implications for both researchers and practitioners in software engineering. This work aims to provide a comprehensive resource for integrating fairness considerations into the development and deployment of machine learning systems, enhancing their reliability, accountability, and credibility.

cs.SE↗

arXiv2025

Reformulating Regression Test Suite Optimization using Quantum Annealing -- an Empirical Study

Maintaining software quality is crucial in the dynamic landscape of software development. Regression testing ensures that software works as expected after changes are implemented. However, re-executing all test cases for every modification is often impractical and costly, particularly for large systems. Although very effective, traditional test suite optimization techniques are often impractical in resource-constrained scenarios, as they are computationally expensive. Hence, quantum computing solutions have been developed to improve their efficiency but have shown drawbacks in terms of effectiveness. We propose reformulating the regression test case selection problem to use quantum computation techniques better. Our objectives are (i) to provide more efficient solutions than traditional methods and (ii) to improve the effectiveness of previously proposed quantum-based solutions. We propose SelectQA, a quantum annealing approach that can outperform the quantum-based approach BootQA in terms of effectiveness while obtaining results comparable to those of the classic Additional Greedy and DIV-GA approaches. Regarding efficiency, SelectQA outperforms DIV-GA and has similar results with the Additional Greedy algorithm but is exceeded by BootQA.

cs.SE↗

arXiv2023

The Quantum Frontier of Software Engineering: A Systematic Mapping Study

Context. Quantum computing is becoming a reality, and quantum software engineering (QSE) is emerging as a new discipline to enable developers to design and develop quantum programs. Objective. This paper presents a systematic mapping study of the current state of QSE research, aiming to identify the most investigated topics, the types and number of studies, the main reported results, and the most studied quantum computing tools/frameworks. Additionally, the study aims to explore the research community's interest in QSE, how it has evolved, and any prior contributions to the discipline before its formal introduction through the Talavera Manifesto. Method. We searched for relevant articles in several databases and applied inclusion and exclusion criteria to select the most relevant studies. After evaluating the quality of the selected resources, we extracted relevant data from the primary studies and analyzed them. Results. We found that QSE research has primarily focused on software testing, with little attention given to other topics, such as software engineering management. The most commonly studied technology for techniques and tools is Qiskit, although, in most studies, either multiple or none specific technologies were employed. The researchers most interested in QSE are interconnected through direct collaborations, and several strong collaboration clusters have been identified. Most articles in QSE have been published in non-thematic venues, with a preference for conferences. Conclusions. The study's implications are providing a centralized source of information for researchers and practitioners in the field, facilitating knowledge transfer, and contributing to the advancement and growth of QSE.

cs.SE↗

arXiv2022

Toward Granular Automatic Unit Test Case Generation

Unit testing verifies the presence of faults in individual software components. Previous research has been targeting the automatic generation of unit tests through the adoption of random or search-based algorithms. Despite their effectiveness, these approaches do not implement any strategy that allows them to create unit tests in a structured manner: indeed, they aim at creating tests by optimizing metrics like code coverage without ensuring that the resulting tests follow good design principles. In order to structure the automatic test case generation process, we propose a two-step systematic approach to the generation of unit tests: we first force search-based algorithms to create tests that cover individual methods of the production code, hence implementing the so-called intra-method tests; then, we relax the constraints to enable the creation of intra-class tests that target the interactions among production code methods.

cs.SE↗

arXiv2022

Software Engineering for Quantum Programming: How Far Are We?

Quantum computing is no longer only a scientific interest but is rapidly becoming an industrially available technology that can potentially overcome the limits of classical computation. Over the last years, all major companies have provided frameworks and programming languages that allow developers to create their quantum applications. This shift has led to the definition of a new discipline called quantum software engineering, which is demanded to define novel methods for engineering large-scale quantum applications. While the research community is successfully embracing this call, we notice a lack of systematic investigations into the state of the practice of quantum programming. Understanding the challenges that quantum developers face is vital to precisely define the aims of quantum software engineering. Hence, in this paper, we first mine all the GitHub repositories that make use of the most used quantum programming frameworks currently on the market and then conduct coding analysis sessions to produce a taxonomy of the purposes for which quantum technologies are used. In the second place, we conduct a survey study that involves the contributors of the considered repositories, which aims to elicit the developers' opinions on the current adoption and challenges of quantum programming. On the one hand, the results highlight that the current adoption of quantum programming is still limited. On the other hand, there are many challenges that the software engineering community should carefully consider: these do not strictly pertain to technical concerns but also socio-technical matters.

cs.SE↗

arXiv2019

Improving Change Prediction Models with Code Smell-Related Information

Code smells represent sub-optimal implementation choices applied by developers when evolving software systems. The negative impact of code smells has been widely investigated in the past: besides developers' productivity and ability to comprehend source code, researchers empirically showed that the presence of code smells heavily impacts the change-proneness of the affected classes. On the basis of these findings, in this paper we conjecture that code smell-related information can be effectively exploited to improve the performance of change prediction models, ie models having as goal that of indicating to developers which classes are more likely to change in the future, so that they may apply preventive maintenance actions. Specifically, we exploit the so-called intensity index - a previously defined metric that captures the severity of a code smell - and evaluate its contribution when added as additional feature in the context of three state of the art change prediction models based on product, process, and developer-based features. We also compare the performance achieved by the proposed model with the one of an alternative technique that considers the previously defined antipattern metrics, namely a set of indicators computed considering the history of code smells in files. Our results report that (i) the prediction performance of the intensity-including models is statistically better than that of the baselines and (ii) the intensity is a more powerful metric with respect to the alternative smell-related ones.

cs.SE↗

arXiv2017

Multiscale simulations of topological transformations in magnetic Skyrmions

Magnetic Skyrmions belong to the most interesting spin structures for the development of future information technology as they have been predicted to be topologically protected. To quantify their stability, we use an innovative multiscale approach to simulating spin dynamics based on the Landau-Lifshitz-Gilbert equation. The multiscale approach overcomes the micromagnetic limitations that have hindered realistic studies using conventional techniques. We first demonstrate how the stability of a Skyrmion is influenced by the refinement of the computational mesh and reveal that conventionally employed traditional micromagnetic simulations are inadequate for this task. Furthermore, we determine the stability quantitatively using our multiscale approach. As a key operation for devices, the process of annihilating a Skyrmion by exciting it with a spin polarized current pulse is analyzed, showing that Skyrmions can be reliably deleted by designing the pulse shape.

cond-mat.mtrl-sci↗

arXiv2016

Multiscale Model Approach for Magnetization Dynamics Simulations

Simulations of magnetization dynamics in a multiscale environment enable rapid evaluation of the Landau-Lifshitz-Gilbert equation in a mesoscopic sample with nanoscopic accuracy in areas where such accuracy is required. We have developed a multiscale magnetization dynamics simulation approach that can be applied to large systems with spin structures that vary locally on small length scales. To implement this, the conventional micromagnetic simulation framework has been expanded to include a multiscale solving routine. The software selectively simulates different regions of a ferromagnetic sample according to the spin structures located within in order to employ a suitable discretization and use either a micromagnetic or an atomistic model. To demonstrate the validity of the multiscale approach, we simulate the spin wave transmission across the regions simulated with the two different models and different discretizations. We find that the interface between the regions is fully transparent for spin waves with frequency lower than a certain threshold set by the coarse scale micromagnetic model with no noticeable attenuation due to the interface between the models. As a comparison to exact analytical theory, we show that in a system with Dzyaloshinskii-Moriya interaction leading to spin spiral, the simulated multiscale result is in good quantitative agreement with the analytical calculation.

physics.comp-ph↗