arXiv subjects

Danilo Monteiro Ribeiro

Publications and source records attributed to Danilo Monteiro Ribeiro.

At least 19 recordsLinked to original sources

arXiv2026

Understanding LLM Usage Among Early-Career Software Engineers in Practice

Despite the rapid adoption of Large Language Models in professional software engineering, limited research has investigated how early career professionals develop effective AI assisted work practices during their transition into industry. We report findings from a mixed methods survey with 75 novice software engineers who actively use LLM supported tools in their daily work. Our results show that LLMs are embedded in routine software engineering activities, including coding, debugging, testing, documentation, and problem solving. Effective use depends on traditional software engineering competencies, such as debugging, testing, and architectural reasoning, together with critical thinking, output verification, prompt engineering, and continuous human oversight. We also identify a gap between workplace expectations and university preparation, with most participants reporting limited formal education on practical LLM use. These findings have implications for software engineering education, organizational onboarding, and workforce development in AI assisted software engineering.

cs.SE↗

arXiv2026

Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews

This study analyses LLMs in imbalanced binary classification, using study screening in systematic reviews as the application domain. An experiment was conducted in five reviews, comparing individual and batch processing, with and without prevalence metadata. The results indicate a limited influence of the prevalence metadata, with no evidence that it improves performance. In contrast, batch processing produced larger behavioral changes that varied according to the prevalence of the class. The aggregate and item-level analyses did not always coincide. Therefore, batch processing should be evaluated not only in terms of cost, but also in relation to its effects on decision-making behavior.

cs.CL↗

arXiv2026

Useful Learning Experiences: A Qualitative Study of Corporate Training in Brazilian Software Engineering

Context: Quantitative studies can identify statistical predictors of training quality, but they often fail to capture what professionals themselves consider genuinely useful learning experiences and why. Objective: This study qualitatively investigates which types of learning experiences are perceived as most useful by Brazilian software engineering professionals and what characteristics define this usefulness. Method: Open-ended responses from 195 software engineering professionals were analyzed using Thematic Analysis, supported by frequency and lemmatization analysis using IRAMUTEQ and co-occurrence analysis between themes. Results: Five themes emerged: Continuous Technical Updating (T1), Practical and Applied Learning (T2), Formal Academic Education (T3), Social Learning and Networking (T4), and Leadership Development and Soft Skills (T5). Technical updating and practical application dominate professionals' accounts. Formal education, social learning, and soft skills are also valued as complementary dimensions. Conclusions: Perceived usefulness is strongly tied to alignment with daily work demands and immediate applicability. The convergence of technical updating (T1) and practical application (T2) in both frequency and co-occurrence reinforces the imperative of continuous learning in software engineering. Useful learning is not reducible to a single modality: genuinely valued experiences span technical, academic, social, and self-directed dimensions. Formal academic education and practical learning are perceived as complementary rather than competing. Organizations should design training ecosystems that integrate these dimensions rather than delivering isolated events.

cs.SE↗

arXiv2026

Verification-Conditioned Use: A Qualitative Study on How Generative AI Reshapes Learning, Autonomy, and Market Entry for Junior Software Developers

Objective: to investigate how the use of generative Artificial Intelligence (AI) tools affects the early stages of a career in software development, from the perspective of the newcomers themselves. Method: thirteen interns and junior developers were interviewed individually, by videoconference. Interviews were analyzed using the six phases of Braun and Clarke's thematic analysis, with inductive coding and a semantic approach. Results: sixteen themes emerged, organized around a central concept: verification-conditioned use. Across the study's four research questions (usage patterns, learning, autonomy, and market entry), the criterion that most often decides between AI and manual work is not deadline or task complexity, but the ability to check the result. Two themes expose tensions in newcomers' self-perception: the autonomy paradox (feeling more capable yet less in ownership of the result) and the first-person denial of dependence. Together, these findings point to a theoretical contribution, the formative paradox: the shallow learning that AI induces makes it harder to build the very critical-judgment competence that, according to participants, the market has begun to demand. Conclusion: what makes AI use sustainable, from participants' own point of view, is not the tool itself but the individual practice of reviewing before accepting, refusing to use AI without understanding it, asking the tool for explanations, and keeping deliberate practice outside of AI-assisted work.

cs.SE↗

arXiv2026

Observing the Conduct of Systematic Reviews with Generative AI Support: An Experience Report from a Graduate Software Engineering Course

Context: Secondary studies are fundamental practices in Evidence- Based Software Engineering, but teaching them requires activities that expose students to authentic methodological decisions. Objective: This paper reports an experience in a graduate course in which ten doctoral students in Software Engineering, organized into three groups, piloted secondary studies with and without support from generative AI. Method: A single-day classroom session was organized and observed, in which the groups conducted pilot systematic reviews with and without generative AI support. Classroom observations, produced artifacts, and interaction threads with assistants configured in ChatGPT were analyzed to reconstruct how each group appropriated the technology throughout the activity. Results: LLMs reduced initial barriers, accelerated the generation of alternatives, and made methodological problems more explicit, but they also favored excessive delegation, superficial validation, operational difficulties, and a shift in focus from conducting the SLR to using the tool. Conclusion: The experience offers a situated, observational account of how doctoral students engaged with generative AI during a systematic review activity, and the resulting insights also inform the design of a subsequent controlled study. The findings indicate that generative AI can support practical learning about SLRs, provided that its use is accompanied by human supervision, decision records, and critical reflection on its limitations.

cs.CY↗

arXiv2026

A Preliminary Study on the Impact of AI in the Creativity and Collaboration in Software Teams

Generative artificial intelligence (GenAI) tools are reshaping software engineering work, increasingly acting as cognitive partners rather than purely instrumental aids. Most AI tooling remains optimized for individual use, yet software development is inherently collaborative and creative, raising open questions about how AI affects team-based work. This paper examines how software engineering professionals perceive and integrate AI tools focusing on creativity and collaboration within teams. We conducted semi-structured interviews with 13 software professionals from four companies, each representing a distinct team. Our analysis identifies three central themes - AI Use, Consequences of AI, and Collaboration and Team Dynamics, alongside Emotions as a cross-cutting dimension. Key findings include: AI broadens developers' creative repertoires but may narrow independent ideation; developers increasingly consult AI instead of colleagues, weakening peer learning and mentoring; and teams are developing emerging triadic collaboration patterns in which developers, colleagues, and AI reason together.

cs.SE↗

arXiv2026

What Does It Take to Research with AI? A Rapid Review of Competencies to Train LLM-Literate Researchers

The growing adoption of Large Language Models in scientific research has created a need to understand what competencies researchers and graduate students require to use these tools critically and responsibly. This rapid review analyzed 194 articles retrieved from Elicit and Google Scholar (2022 to 2025), from which 40 were selected for competency extraction and thematic analysis following independent dual screening (Gwet AC1: 0.76 to 0.83). Eight competencies were identified. The most prevalent was domain expertise and oversight of AI outputs (n = 123), encompassing subject matter mastery, systematic skepticism, source verification, and researcher accountability. Other key competencies include metacognition and decision making about AI use (n = 55), ethics and academic integrity (n = 53), prompt engineering for research (n = 38), and reproducibility of AI use (n = 29). AI literacy and technical knowledge (n = 16) was explicitly identified as a risk factor when absent, with domain expertise treated as a prerequisite for meaningful critical evaluation. The findings suggest that preparing researchers to use LLMs goes beyond technical instruction, requiring an integrated set of epistemic, ethical, and methodological competencies centered on human accountability for the knowledge produced. These results have direct implications for the design of graduate programs and AI literacy initiatives.

cs.SE↗

arXiv2026

Beyond Accuracy: LLM Variability in Evidence Screening for Software Engineering SLRs

Context: Study screening in systematic literature reviews is costly, inconsistency-prone, and risk-asymmetric, since false negatives can compromise validity. Despite rapid uptake of Large Language Models (LLMs), there is limited evidence on how such models behave during the study screening phase, particularly regarding the choice of specific LLMs and their comparison with classical models. Objective: To assess LLM performance and variability in screening, quantify the impact of input metadata (abstract, title, keywords), and compare LLMs with classical classifiers under a shared protocol. Methods: We analyzed 12 LLMs from 4 providers (OpenAI, Google Gemini, Anthropic, Llama) and 4 classical models (Logistic Regression, Support Vector Classification, Random Forest, and Naive Bayes) on 2 real Systematic Literature Reviews (SLRs), totaling 518 papers. The experimental design investigated 3 critical dimensions: (i) LLMs performance variability, (ii) the impact of input feature composition (abstract, title, and keywords) on LLM performance, and (iii) the real gain of using LLMs instead of more traditional classification models. Results: LLMs exhibited substantial heterogeneity and residual non-determinism even at temperature zero. Abstract availability was decisive: removing it consistently degraded performance, while adding title and/or keywords to the abstract yielded no robust gains. Compared to classical models, performance differences were not consistent enough to support generalizable LLM superiority. Discussion: LLM adoption should be justified by operational and governance constraints (reproducibility, cost, metadata availability), supported by pilot validation and explicit reporting of variability and input configuration.

cs.SE↗

arXiv2026

It's Not About Whom You Train: An Analysis of Corporate Education in Software Engineering

Context: Corporate education is a strategic investment in the software industry, but little is known about how different professional profiles perceive these initiatives. Objective: To investigate whether sociodemographic and professional variables influence the perception of quality and effectiveness of corporate training in Software Engineering (SE). Method: Non-parametric significance tests were applied to data from a survey with 282 Brazilian professionals, crossing 27 perception items with 9 sociodemographic variables (gender, age, education level, state, experience, professional level, company size, area of work, and nature of participation), totaling 243 combinations. Results: Of the 243 combinations tested, only 35 showed statistical significance. Training mandatoriness was the dominant factor, affecting 24 of 27 items. Length of experience revealed a non-linear descriptive pattern with a low-engagement zone between 3 and 6 years. Differences by area of work indicated an expressive gap in soft skills training for advanced technical roles. Personal profile variables and company size produced no relevant significant differences. Conclusion: Personal profile variables do not determine the perception of quality and effectiveness, while professional trajectory variables (experience, level, area of work) produce localized differences. The voluntariness of participation remains a determining factor, in line with the literature. The absence of gender differences in a sample with 23\% women suggests that barriers operate before training, in access and representation, not during the learning experience.

cs.SE↗

arXiv2026

Corporate Training in Brazilian Software Engineering: A Quantitative Study of Professional Perceptions

Context: Strategic corporate training is essential for the sustained professional development of software engineers. However, there is a knowledge gap regarding the factors that drive quality and effectiveness of such training from the professionals' perspective, and no validated instrument exists for assessing these factors in the software engineering (SE) domain. Objective: This study aims to quantitatively analyze which factors influence SE professionals' perceptions of corporate training quality and effectiveness. Method: A quantitative survey was conducted with 282 Brazilian SE professionals. A structured questionnaire was developed and polychoric correlation was adopted for data analysis. Results: Three tightly correlated factors (cognitive engagement, variety of activities, and instructor performance) emerged as the strongest predictors of perceived training quality and effectiveness. Mandatory participation significantly reduces motivation and perceived training quality. Perceived impact on personal time proved to be largely independent of training quality. These findings are consistent with the general training effectiveness literature. Conclusions: Training effectiveness in the SE context is predominantly determined by three factors: cognitive engagement, variety of activities, and instructor performance. Mandatory participation negatively influences motivation, perceived relevance, and perceived training quality, while also amplifying the perception of time burden. The consistency with the general literature suggests that software organizations do not need to reinvent training design principles and can apply established guidelines with confidence. Salas and Cannon-Bowers' framework produced coherent results in the SE context, making it a promising candidate for future psychometric validation.

cs.SE↗

arXiv2026

The professional's opinion: Suggestions for improving the corporate education training process in Software Engineering

Technology organizations continuously invest in professional development, but face difficulties in transferring learning to project practice. This exploratory qualitative study investigates which improvements software engineering professionals suggest for organizational learning processes. 174 open-ended responses were analyzed through reflexive thematic analysis. Five themes emerged: practical applicability and alignment with needs; pedagogical quality and organization; time and structural conditions; incentives and institutional recognition; and interaction, mentoring, and social exchange. The results indicate that improving learning requires systemic interventions that integrate practical relevance, structural support, and a favorable institutional culture.

cs.SE↗

arXiv2025

A Mapping Study About Training in Industry Context in Software Engineering

Context: Corporate training plays a strategic role in the continuous development of professionals in the software engineering industry. However, there is a lack of systematized understanding of how training initiatives are designed, implemented, and evaluated within this domain. Objective: This study aims to map the current state of research on corporate training in software engineering in industry settings, using Eduardo Salas' training framework as an analytical lens. Method: A systematic mapping study was conducted involving the selection and analysis of 26 primary studies published in the field. Each study was categorized according to Salas' four key areas: Training Needs Analysis, Antecedent Training Conditions, Training Methods and Instructional Strategies, and Post-Training Conditions. Results: The findings show a predominance of studies focusing on Training Methods and Instructional Strategies. Significant gaps were identified in other areas, particularly regarding Job/Task Analysis and Simulation-based Training and Games. Most studies were experience reports, lacking methodological rigor and longitudinal assessment. Conclusions: The study offers a structured overview of how corporate training is approached in software engineering, revealing underexplored areas and proposing directions for future research. It contributes to both academic and practical communities by highlighting challenges, methodological trends, and opportunities for designing more effective training programs in industry.

cs.SE↗

arXiv2025

Understanding the relationships between the perceptions of burnout and instability in Software Engineering

Changes are inherent in software development, often increasing developers' perception of instability. Understanding the relationship between human factors and Software Engineering processes is crucial to mitigating and preventing issues. One such factor is burnout, a recognized disease that impacts productivity, turnover, and, most importantly, developers' well-being. Investigating the link between instability and burnout can help organizations implement strategies to improve developers' work conditions and performance. This study aims to identify and describe the relationship between perceived instability and burnout among software developers. A cross-sectional survey was conducted with 411 respondents, using convenience sampling and self-selection. In addition to analyzing variable relationships, confirmatory factor analysis was applied. Key findings include: (1) A significant positive relationship between burnout (exhaustion and cynicism) and team, technological, and task instability; (2) A weak negative relationship between efficacy and technological/team instability, with no correlation to task instability; (3) Exhaustion was the most frequently reported burnout symptom, while task instability was the most perceived type of instability. These results are valuable for both industry and academia, providing insights to reduce burnout and instability among software engineers. Future research can further explore the impact of instability, offering new perspectives on monitoring and mitigating its effects in software development.

cs.SE↗

arXiv2024

A Comparative Study on Accessibility for Autistic Individuals with Urban Mobility Apps

Autism Spectrum Disorder (ASD) is a neurodivergent condition with a wide range of characteristics and support levels. Individuals with ASD can exhibit various combinations of traits such as difficulties in social interaction, communication, and language, alongside restricted interests and repetitive activities. Many adults with ASD live independently due to increased awareness and late diagnoses, which help them manage long-standing challenges. Predictability, clarity, and minimized sensory stimuli are crucial for the daily comfort of autistic individuals. In mobile applications, autistic users face significant cognitive overload compared to neurotypicals, resulting in higher effort and time to complete tasks. Urban mobility apps, essential for daily routines, often overlook the needs of autistic users, leading to cognitive overload issues. This study investigates the accessibility of urban mobility apps for autistic individuals using the Interfaces Accessibility Guide for Autism (GAIA). By evaluating various apps, we have identified a common gap regarding accessibility for people with Autism Spectrum Disorder (ASD). This limitation relates to the absence of a functionality that allows users on the autism spectrum to customize the characteristics of the textual and visual elements of the software, such as changing the text font, altering the font type, and adjusting text colors, as well as native audio guidance within the applications themselves. Currently, the only function in this context is for visually impaired people, which completely changes the user experience in terms of navigation.

cs.HC↗

arXiv2024

An Actionable Framework for Understanding and Improving Talent Retention as a Competitive Advantage in IT Organizations

In the rapidly evolving global business landscape, the demand for software has intensified competition among organizations, leading to challenges in retaining highly qualified IT members in software organizations. One of the problems faced by IT organizations is the retention of these strategic professionals, also known as talent. This work presents an actionable framework for Talent Retention (TR) used in IT organizations. It is based on our findings from interviews performed with 21 IT managers. The TR Framework is our main research outcome. Our framework encompasses a set of factors, contextual characteristics, barriers, strategies, and coping mechanisms. Our findings indicated that software engineers can be differentiated from other professional groups, and beyond competitive salaries, other elements for retaining talent in IT organizations should be considered, such as psychological safety, work-life balance, a positive work environment, innovative and challenging projects, and flexible work. A better understanding of factors could guide IT managers in improving talent management processes by addressing Software Engineering challenges, identifying important elements, and exploring strategies at the individual, team, and organizational levels.

cs.SE↗

arXiv2023

Large Language Models for Education: Grading Open-Ended Questions Using ChatGPT

As a way of addressing increasingly sophisticated problems, software professionals face the constant challenge of seeking improvement. However, for these individuals to enhance their skills, their process of studying and training must involve feedback that is both immediate and accurate. In the context of software companies, where the scale of professionals undergoing training is large, but the number of qualified professionals available for providing corrections is small, delivering effective feedback becomes even more challenging. To circumvent this challenge, this work presents an exploration of using Large Language Models (LLMs) to support the correction process of open-ended questions in technical training. In this study, we utilized ChatGPT to correct open-ended questions answered by 42 industry professionals on two topics. Evaluating the corrections and feedback provided by ChatGPT, we observed that it is capable of identifying semantic details in responses that other metrics cannot observe. Furthermore, we noticed that, in general, subject matter experts tended to agree with the corrections and feedback given by ChatGPT.

cs.SE↗

arXiv2023

Understanding Self-Efficacy in the Context of Software Engineering: A Qualitative Study in the Industry

CONTEXT: Self-efficacy is a concept researched in various areas of knowledge that impacts various factors such as performance, satisfaction, and motivation. In Software Engineering, it has mainly been studied in the academic context, presenting results similar to other areas of knowledge. However, it is also important to understand its impact in the industrial context. OBJECTIVE: Therefore, this study aims to understand the impact on the software development context with a focus on understanding the behavioral signs of self-efficacy in software engineers and how self-efficacy can impact the work-day of software engineers. METHOD: A qualitative research was conducted using semi-structured questionnaires with 31 interviewees from a software development company located in Brazil. The interviewees participated in a Bootcamp and were later assigned to software development teams. Thematic analysis was used to analyze the data. RESULTS: In the perception of the interviewees, 21 signs were found that are related to people with high and low self-efficacy. These signs were divided into two dimensions: social and cognitive. Also, 18 situations were found that can lead to an increase or decrease of self-efficacy of software engineers. Finally, 12 factors were mentioned that can impact software development teams. CONCLUSION: This work evidences a set of behavioral signs that can help team leaders to better perceive the self-efficacy of their members. It also presents a set of situations that both leaders and individuals can use to improve their self-efficacy in the development context, and finally, factors that can be impacted by self-efficacy in the software development context are also presented. Finally, this work emphasizes the importance of understanding self-efficacy in the industrial context.

cs.SE↗

arXiv2023

Supporting the Careers of Developers with Disabilities: Lessons from Zup Innovation

People with still face discrimination, which creates significant obstacles to accessing higher education, ultimately hindering their access to high-skilled occupations. In this study we present Catalisa, an eight-month training camp (developed by Zup Innovation) that hires and trains people with disabilities as software developers. We interviewed 12 Catalisa participants to better understand their challenges and limitations regarding inclusion and accessibility. We offer four recommendations to improve inclusion and accessibility in Catalisa-like programs, that we hope could motive others to build a more inclusive and equitable workplace that benefits everyone.

cs.SE↗