Kleinner Silva Farias De Oliveira · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.24884 · cited by 0 works (OpenAlex) · open-access PDF
Mit dem Aufkommen der spezifikationsgetriebenen Entwicklung (SDD) hat die Software-Modellierung strategische Bedeutung wiedergewonnen als eine Möglichkeit, menschliche Absichten, Anforderungen und Entwurfsentscheidungen in präzise Spezifikationen zu übersetzen, die sowohl Entwickler als auch AI-unterstützte Entwicklungswerkzeuge leiten können. Trotz der erneuerten Relevanz der Modellierung in SDD bleiben die empirischen Beweise begrenzt, wenn ihre Vorteile die sozio-technischen Anstrengungen übertreffen, die erforderlich sind, um Software-Modelle in der industriellen Praxis zu erstellen, zu kommunizieren, zu synchronisieren und zu pflegen. Diese Studie untersucht, wann Software-Modellierung in der industriellen Praxis Wert erzeugt. Wir analysi
Machine translation (Meta M2M100); the English original follows.
With the emergence of specification-driven development (SDD), software modeling has regained strategic importance as a way to translate human intentions, requirements, and design decisions into precise specifications that can guide both developers and AI-assisted development tools. Despite the renewed relevance of modeling in SDD, empirical evidence remains limited on when its benefits outweigh the socio-technical effort required to create, communicate, synchronize, and maintain software models in industrial practice. This study investigates when software modeling generates value in industrial practice. We analyzed 405 survey responses collected from software practitioners. The questionnaire combined closed items concerning UML use, benefits, barriers, and improvement mechanisms with open-ended questions about current use, difficulties, and worthwhile contexts. Most respondents associated modeling with integration discussions (90 percent) and shared understanding (82 percent), but also reported time pressure (85 percent) and the effort required to create and maintain models (80 percent). Selective modeling, model-code synchronization, and collaborative support emerged as conditions that improve its viability, whereas only 24 percent reported daily UML use. Software modeling pays off when its expected contextual value exceeds the socio-technical friction required to create and sustain it. Its value is therefore contingent, not universal.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Unified Modeling Language, Computer science, Software development, Software engineering, Software, Relevance (law)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.24884, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange