Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Software Engineering Techniques and PracticesSoftware Engineering Research
Abstract
Vorlage für die Softwareentwicklung mit Sprachmodell-Agenten, bei der die Rolle, die Code schreibt, ihn nicht selbst abnimmt. Ein Bash-Orchestrator führt jeden Meilenstein durch feste Phasen mit getrennten Rollen: Ein Builder plant und programmiert, ein Reviewer schreibt vor der Umsetzung ausführbare Abnahmetests und prüft Plan und Code, eine optionale QA-Rolle sucht reproduzierbare Gegenbeispiele. Es sind Rollen, nicht zwingend verschiedene Modelle; welches Modell welche Rolle ausführt, legt der Betreiber in der Konfiguration fest. Nach jedem Modellaufruf prüft der Orchestrator per Git, dass die Rolle nur in ihrem Bereich geschrieben hat, und verwirft Verstöße. Abgeschlossen wird ein Meilenstein nur, wenn die vom Betreiber gewählten ausführbaren Prüfungen (Gate-Skripte, etwa Tests, Lint oder Mutationstests) bestehen und der Reviewer zustimmt; ein Modellurteil allein genügt nie. Die Spezifikation ändert nur der Mensch; was eine Schiedsrichter-Sitzung nicht auflösen kann, wird geparkt und als Eskalation an den Menschen übergeben. Selbsttests mit Modellattrappen prüfen die Ablauflogik ohne Modellaufrufe. Prototyp; mit agentengestützter Codeerzeugung entstanden, Dokumentation auf Deutsch. A template for developing software with language-model agents in which the role that writes the code never accepts it. A Bash orchestrator drives each milestone through fixed phases with separate roles: a builder plans and implements, a reviewer writes executable acceptance tests before implementation and reviews the plan and the code, and an optional QA role searches for reproducible counterexamples. These are roles, not necessarily different models; the operator decides in the configuration which model runs which role. After every model call, the orchestrator uses Git to check that the role wrote only within its own territory and discards violations. A milestone is completed only when the executable checks selected by the operator (gate scripts such as tests, linting or mutation testing) pass and the reviewer approves; a model verdict alone is never sufficient. Only the human operator changes the specification; disputes that an arbiter session cannot resolve are parked and handed to the human as an escalation. Self-tests with stub models exercise the orchestration logic without any model calls. Prototype, developed with agent-assisted code generation; documentation in German.
This publication proposes a definition and a classification of agile software development approaches and analyses ten software development methods that can be characterized as being "agile" against the defined criterion.
P. Abrahamsson, O. Salo, Jussi Ronkainen et al.· arXiv.org· 727 citations· ⚡54
The study shows that agile practices improve both informal and formal communication, but indicates that, in larger development situations involving multiple external stakeholders, a mismatch of adequate communication mechanisms can sometimes even hinder the communication.
M. Pikkarainen, Jukka Haikara, O. Salo et al.· Empirical Software Engineeri...· 401 citations· ⚡48
The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.
Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al.· Information and Software Tec...· 394 citations· ⚡54
The results show that the embedded industry has been able to apply agile methods in its development processes and that the appreciation of the agile methods and their individual practices appears to increase once adopted and applied in practice.
O. Salo, P. Abrahamsson· IET Software· 238 citations· ⚡9
Consequences of happiness and unhappiness that are beneficial and detrimental for developers' mental well-being, the software development process, and the produced artifacts are found.
D. Graziotin, Fabian Fagerholm, Xiaofeng Wang et al.· Journal of Systems and Softw...· 236 citations· ⚡13
The Mobile-D approach is briefly outlined here and the experiences gained from four case studies are discussed, which helped develop an agile development approach for mobile application development.
P. Abrahamsson, Antti Hanhineva, H. Hulkko et al.· Conference on Object-Oriente...· 225 citations· ⚡18
Related blog posts
Microsoft Research Blog· microsoft.comOct 12, 2026
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.