Hasil untuk "Industrial engineering. Management engineering"

Junjie Shi, Weisong Sun, Zhenpeng Chen et al.

The rapid development of large language models is transforming software development. Beyond serving as code auto-completion tools in integrated development environments, large language models increasingly function as foundation models within coding agents in vibe-coding scenarios. In such settings, prompts play a central role in agent-based intelligent software development, as they not only guide the behavior of large language models but also serve as carriers of user requirements. Under the dominant conversational paradigm, prompts are typically divided into system prompts and user prompts. System prompts provide high-level instructions to steer model behavior and establish conversational context, while user prompts represent inputs and requirements provided by human users. Despite their importance, designing effective prompts remains challenging, as it requires expertise in both prompt engineering and software engineering, particularly requirements engineering. To reduce the burden of manual prompt construction, numerous automated prompt engineering methods have been proposed. However, most existing approaches neglect the methodological principles of requirements engineering, limiting their ability to generate artifacts that conform to formal requirement specifications in realistic software development scenarios. To address this gap, we propose REprompt, a multi-agent prompt optimization framework guided by requirements engineering. Experiment results demonstrate that REprompt effectively optimizes both system and user prompts by grounding prompt generation in requirements engineering principles.

Cristina Martinez Montes, Robert Feldt, Cristina Miguel Martos et al.

As artificial intelligence advances, large language models (LLMs) are entering qualitative research workflows, yet no reproducible methods exist for integrating them into established approaches like thematic analysis (TA), one of the most common qualitative methods in software engineering research. Moreover, existing studies lack systematic evaluation of LLM-generated qualitative outputs against established quality criteria. We designed and iteratively refined prompts for Phases 2-5 of Braun and Clarke's reflexive TA, then tested outputs from multiple LLMs against codes and themes produced by experienced researchers. Using 15 interviews on software engineers' well-being, we conducted blind evaluations with four expert evaluators who applied rubrics derived directly from Braun and Clarke's quality criteria. Evaluators preferred LLM-generated codes 61% of the time, finding them analytically useful for answering the research question. However, evaluators also identified limitations: LLMs fragmented data unnecessarily, missed latent interpretations, and sometimes produced themes with unclear boundaries. Our contributions are threefold. First, a reproducible approach integrating refined, documented prompts with an evaluation framework to operationalize Braun and Clarke's reflexive TA. Second, an empirical comparison of LLM- and human-generated codes and themes in software engineering data. Third, guidelines for integrating LLMs into qualitative analysis while preserving methodological rigour, clarifying when and how LLMs can assist effectively and when human interpretation remains essential.

Christoph Treude, Raula Gaikovina Kula

Recent advances in AI reasoning models provide unprecedented transparency into their decision-making processes, transforming them from traditional black-box systems into models that articulate step-by-step chains of thought rather than producing opaque outputs. This shift has the potential to improve software quality, explainability, and trust in AI-augmented development. However, software engineers rarely have the time or cognitive bandwidth to analyze, verify, and interpret every AI-generated thought in detail. Without an effective interface, this transparency could become a burden rather than a benefit. In this paper, we propose a vision for structuring the interaction between AI reasoning models and software engineers to maximize trust, efficiency, and decision-making power. We argue that simply exposing AI's reasoning is not enough -- software engineers need tools and frameworks that selectively highlight critical insights, filter out noise, and facilitate rapid validation of key assumptions. To illustrate this challenge, we present motivating examples in which AI reasoning models state their assumptions when deciding which external library to use and produce divergent reasoning paths and recommendations about security vulnerabilities, highlighting the need for an interface that prioritizes actionable insights while managing uncertainty and resolving conflicts. We then outline a research roadmap for integrating automated summarization, assumption validation, and multi-model conflict resolution into software engineering workflows. Achieving this vision will unlock the full potential of AI reasoning models to enable software engineers to make faster, more informed decisions without being overwhelmed by unnecessary detail.

Carl Philipp Hohl, Philipp Reis, Tobias Schürmann et al.

Vehicle data is essential for advancing data-driven development throughout the automotive lifecycle, including requirements engineering, design, verification, and validation, and post-deployment optimization. Developers currently collect data in a decentralized and fragmented manner across simulations, test benches, and real-world driving, resulting in data silos, inconsistent formats, and limited interoperability. This leads to redundant efforts, inefficient integration, and suboptimal use of data. This fragmentation results in data silos, inconsistent storage structures, and limited interoperability, leading to redundant data collection, inefficient integration, and suboptimal application. To address these challenges, this article presents a structured literature review and develops an inductive taxonomy for automotive data. This taxonomy categorizes data according to its sources and applications, improving data accessibility and utilization. The analysis reveals a growing emphasis on real-world driving and machine learning applications while highlighting a critical gap in data availability for requirements engineering. By providing a systematic framework for structuring automotive data, this research contributes to more efficient data management and improved decision-making in the automotive industry.

Vahid Salehi, Josef Vilsmeier, Shirui Wang

Today, products are no longer isolated artifacts, but nodes in networked systems. This means that traditional, linearly conceived life cycle models are reaching their limits: Interoperability across disciplines, variant and configuration management, traceability, and governance across organizational boundaries are becoming key factors. This collective contribution classifies the state of the art and proposes a practical frame of reference for SoS lifecycle management, model-based systems engineering (MBSE) as the semantic backbone, product lifecycle management (PLM) as the governance and configuration level, CAD-CAE as model-derived domains, and digital thread and digital twin as continuous feedback. Based on current literature and industry experience, mobility, healthcare, and the public sector, we identify four principles: (1) referenced architecture and data models, (2) end-to-end configuration sovereignty instead of tool silos, (3) curated models with clear review gates, and (4) measurable value contributions along time, quality, cost, and sustainability. A three-step roadmap shows the transition from product- to network- centric development: piloting with reference architecture, scaling across variant and supply chain spaces, organizational anchoring (roles, training, compliance). The results are increased change robustness, shorter throughput times, improved reuse, and informed sustainability decisions. This article is aimed at decision-makers and practitioners who want to make complexity manageable and design SoS value streams to be scalable.

Breno Bernard Nicolau de França, Dietmar Pfahl, Valdemar Vicente Graciano Neto et al.

The chapter supports educators and postgraduate students in understanding the role of simulation in software engineering research based on the authors' experience. This way, it includes a background positioning simulation-based studies in software engineering research, the proposition of learning objectives for teaching simulation as a research method, and presents our experience when teaching simulation concepts and practice. For educators, it further provides learning objectives when teaching simulation, considering the current state of the art in software engineering research and the necessary guidance and recommended learning activities to achieve these objectives. For students, it drives the learning path for those interested in learning this method but had no opportunity to engage in an entire course on simulation in the context of empirical research.

Pragya Verma, Marcos Vinicius Cruz, Grischa Liebel

Neurodiversity describes variation in brain function among people, including common conditions such as Autism spectrum disorder (ASD), Attention deficit hyperactivity disorder (ADHD), and dyslexia. While Software Engineering (SE) literature has started to explore the experiences of neurodivergent software engineers, there is a lack of research that compares their challenges to those of neurotypical software engineers. To address this gap, we analyze existing data from the 2022 Stack Overflow Developer survey that collected data on neurodiversity. We quantitatively compare the answers of professional engineers with ASD (n=374), ADHD (n=1305), and dyslexia (n=363) with neurotypical engineers. Our findings indicate that neurodivergent engineers face more difficulties than neurotypical engineers. Specifically, engineers with ADHD report that they face more interruptions caused by waiting for answers, and that they less frequently interact with individuals outside their team. This study provides a baseline for future research comparing neurodivergent engineers with neurotypical ones. Several factors in the Stack Overflow survey and in our analysis are likely to lead to conservative estimates of the actual effects between neurodivergent and neurotypical engineers, e.g., the effects of the COVID-19 pandemic and our focus on employed professionals.

Amna Pir Muhammad, Eric Knauss, Jonas Bärgman et al.

Due to the technical complexity and social impact, automated vehicle (AV) development challenges the current state of automotive engineering practice. Research shows that it is important to consider human factors (HF) knowledge when developing AVs to make them safe and accepted. This study explores the current practices and challenges of the automotive industries for incorporating HF requirements during agile AV development. We interviewed ten industry professionals from several Swedish automotive companies, including HF experts and AV engineers. Based on our qualitative analysis of the semi-structured interviews, a number of current approaches for communicating and incorporating HF knowledge into agile AV development and associated challenges are discussed. Our findings may help to focus future research on issues that are critical to effectively incorporate HF knowledge into agile AV development.

Alex Nathan, Dimosthenis Kaponis, Saul Lustgarten

This paper addresses the issue of blockchain protocol risks, a foundational category of risks affecting Distributed Ledger Technology (DLT) which underpins digital assets, smart contracts, and decentralised applications. It presents a comprehensive risk management framework developed in collaboration with financial institutions, blockchain development teams and regulators that applies a traditional risk management taxonomy to address certain overlooked blockchain protocol risks. The approach offers a structured way to identify, measure, monitor and report blockchain protocol risks. The paper provides real-world use cases to demonstrate the practicality and implementation of the proposed framework. The findings of this work contribute to the evolving understanding of blockchain protocol risks and provide valuable insights on how these risks affect the adoption of DLT by financial institutions.

Zoe Kotti, Rafaila Galanopoulou, Diomidis Spinellis

Machine learning (ML) techniques increase the effectiveness of software engineering (SE) lifecycle activities. We systematically collected, quality-assessed, summarized, and categorized 83 reviews in ML for SE published between 2009-2022, covering 6,117 primary studies. The SE areas most tackled with ML are software quality and testing, while human-centered areas appear more challenging for ML. We propose a number of ML for SE research challenges and actions including: conducting further empirical validation and industrial studies on ML; reconsidering deficient SE methods; documenting and automating data collection and pipeline processes; reexamining how industrial practitioners distribute their proprietary data; and implementing incremental ML approaches.

Dennis Müller, Maurice Chiodo, James Franklin

While the consequences of mathematically-based software, algorithms and strategies have become ever wider and better appreciated, ethical reflection on mathematics has remained primitive. We review the somewhat disconnected suggestions of commentators in recent decades with a view to piecing together a coherent approach to ethics in mathematics. Calls for a Hippocratic Oath for mathematicians are examined and it is concluded that while lessons can be learned from the medical profession, the relation of mathematicians to those affected by their work is significantly different. There is something to be learned also from the codes of conduct of cognate but professionalised quantitative disciplines such as engineering and accountancy, as well as from legal principles bearing on professional work. We conclude with recommendations that professional societies in mathematics should sponsor an (international) code of ethics, institutional mission statements for mathematicians and syllabuses for incorporation into mathematics degrees.

Ehsan Zabardast, Julian Frattini, Javier Gonzalez-Huerta et al.

During the development and maintenance of software-intensive products or services, we depend on various artefacts. Some of those artefacts, we deem central to the feasibility of a project and the product's final quality. Typically, these central artefacts are referred to as assets. However, despite their central role in the software development process, little thought is yet invested into what eventually characterises as an asset, often resulting in many terms and underlying concepts being mixed and used inconsistently. A precise terminology of assets and related concepts, such as asset degradation, are crucial for setting up a new generation of cost-effective software engineering practices. In this position paper, we critically reflect upon the notion of assets in software engineering. As a starting point, we define the terminology and concepts of assets and extend the reasoning behind them. We explore assets' characteristics and discuss what asset degradation is as well as its various types and the implications that asset degradation might bring for the planning, realisation, and evolution of software-intensive products and services over time. We aspire to contribute to a more standardised definition of assets in software engineering and foster research endeavours and their practical dissemination in a common, more unified direction.

Javier Gonzalez-Huerta, Jefferson Seide Molleri, Aivars Šablis et al.

Background: Software project management activities help to introduce software process models in Software Engineering courses. However, these activities should be adequately aligned with the learning outcomes and support student's progression. Objective: Present and evaluate an approach to help students acquire theoretical and practical knowledge and experience real-world software projects' challenges. The approach combines a serious game and a design-implement task in which students develop a controlled-scale software system. Method: To evaluate our approach, we analyzed the students' perceptions collected through an online survey, their project plans, and their final reports using thematic analysis. Results: Results suggest that the approach promotes knowledge acquisition, enables students' progression, reinforces theoretical concepts, and is properly aligned with the course's learning outcomes. Conclusion: The approach seems to help to introduce software process models in Software Engineering courses. Our experience can also be inspiring for educators willing to apply our approach in similar courses.

Linda Erlenhov, Francisco Gomes de Oliveira Neto, Philipp Leitner

Software engineering bots - automated tools that handle tedious tasks - are increasingly used by industrial and open source projects to improve developer productivity. Current research in this area is held back by a lack of consensus of what software engineering bots (DevBots) actually are, what characteristics distinguish them from other tools, and what benefits and challenges are associated with DevBot usage. In this paper we report on a mixed-method empirical study of DevBot usage in industrial practice. We report on findings from interviewing 21 and surveying a total of 111 developers. We identify three different personas among DevBot users (focusing on autonomy, chat interfaces, and "smartness"), each with different definitions of what a DevBot is, why developers use them, and what they struggle with. We conclude that future DevBot research should situate their work within our framework, to clearly identify what type of bot the work targets, and what advantages practitioners can expect. Further, we find that there currently is a lack of general purpose "smart" bots that go beyond simple automation tools or chat interfaces. This is problematic, as we have seen that such bots, if available, can have a transformative effect on the projects that use them.

Kushal Singla, Joy Bose, Chetan Naik

The number of machine learning, artificial intelligence or data science related software engineering projects using Agile methodology is increasing. However, there are very few studies on how such projects work in practice. In this paper, we analyze project issues tracking data taken from Scrum (a popular tool for Agile) for several machine learning projects. We compare this data with corresponding data from non-machine learning projects, in an attempt to analyze how machine learning projects are executed differently from normal software engineering projects. On analysis, we find that machine learning project issues use different kinds of words to describe issues, have higher number of exploratory or research oriented tasks as compared to implementation tasks, and have a higher number of issues in the product backlog after each sprint, denoting that it is more difficult to estimate the duration of machine learning project related tasks in advance. After analyzing this data, we propose a few ways in which Agile machine learning projects can be better logged and executed, given their differences with normal software engineering projects.

Simone Romano, Giuseppe Scanniello, Davide Fucci et al.

Background: Noise, defined as an unwanted sound, is one of the commonest factors that could affect people's performance in their daily work activities. The software engineering research community has marginally investigated the effects of noise on software engineers' performance. Aims: We studied if noise affects software engineers' performance in (i) comprehending functional requirements and (ii) fixing faults in the source code. Method: We conducted two experiments with final-year undergraduate students in Computer Science. In the first experiment, we asked 55 students to comprehend functional requirements exposing them or not to noise, while in the second experiment 42 students were asked to fix faults in Java code. Results: The participants in the second experiment, when exposed to noise, had significantly worse performance in fixing faults in the source code. On the other hand, we did not observe any statistically significant difference in the first experiment. Conclusions: Fixing faults in source code seems to be more vulnerable to noise than comprehending functional requirements.

Manuel Mazzara, Kevin Khanda, Ruslan Mustafin et al.

In this paper we offer an overview on the topic of Microservices Science and Engineering (MSE) and we provide a collection of bibliographic references and links relevant to understand an emerging field. We try to clarify some misunderstandings related to microservices and Service-Oriented Architectures, and we also describe projects and applications our team have been working on in the recent past, both regarding programming languages construction and intelligent buildings.

Daisie Huang, Hilmar Lapp

The vast majority of the long tail of scientific software, the myriads of tools that implement the many analysis and visualization methods for different scientific fields, is highly specialized, purpose-built for a research project, and has to rely on community uptake and reuse for its continued development and maintenance. Although uptake cannot be controlled over even guaranteed, some of the key factors that influence whether new users or developers decide to adopt an existing tool or start a new one are about how easy or difficult it is to use or enhance a tool for a purpose for which it was not originally designed. The science of software engineering has produced techniques and practices that would reduce or remove a variety of barriers to community uptake of software, but for a variety of reasons employing trained software engineers as part of the development of long tail scientific software has proven to be challenging. As a consequence, community uptake of long tail tools is often far more difficult than it would need to be, even though opportunities for reuse abound. We discuss likely reasons why employing software engineering in the long tail is challenging, and propose that many of those obstacles could be addressed in the form of a cross-cutting non-profit center of excellence that makes software engineering broadly accessible as a shared service, conceptually and in its effect similar to shared instrumentation.

Thilo Breitsprecher, Mihai Codescu, Constantin Jucovschi et al.

The engineering design process follows a series of standardized stages of development, which have many aspects in common with software engineering. Among these stages, the principle solution can be regarded as an analogue of the design specification, fixing as it does the way the final product works. It is usually constructed as an abstract sketch (hand-drawn or constructed with a CAD system) where the functional parts of the product are identified, and geometric and topological constraints are formulated. Here, we outline a semantic approach where the principle solution is annotated with ontological assertions, thus making the intended requirements explicit and available for further machine processing; this includes the automated detection of design errors in the final CAD model, making additional use of a background ontology of engineering knowledge. We embed this approach into a document-oriented design workflow, in which the background ontology and semantic annotations in the documents are exploited to trace parts and requirements through the design process and across different applications.

Serge Autexier, Catalin David, Dominik Dietrich et al.

Mathematical knowledge is a central component in science, engineering, and technology (documentation). Most of it is represented informally, and -- in contrast to published research mathematics -- subject to continual change. Unfortunately, machine support for change management has either been very coarse grained and thus barely useful, or restricted to formal languages, where automation is possible. In this paper, we report on an effort to extend change management to collections of semi-formal documents which flexibly intermix mathematical formulas and natural language and to integrate it into a semantic publishing system for mathematical knowledge. We validate the long-standing assumption that the semantic annotations in these flexiformal documents that drive the machine-supported interaction with documents can support semantic impact analyses at the same time. But in contrast to the fully formal setting, where adaptations of impacted documents can be automated to some degree, the flexiformal setting requires much more user interaction and thus a much tighter integration into document management workflows.