SAGAI’26 - Fraunhofer IESE

Workshop / June 22, 2026 - June 23, 2026

SAGAI 2026

SAGAI 2026 is over. Thank you to all participants!

We look forward to seeing you next year in SAGAI 2027. Information about SAGAI 2027 will soon be on this website.

Generative AI has become a pervasive topic in recent years, attracting the attention of researchers and practitioners. As the software engineering community begins to explore it, there is a pressing need for developments and contributions from the software architecture community. SAGAI 2026, the 2nd International Workshop on Software Architecture and Generative AI, aims at the consolidation of a community dedicated to exploring the opportunities and limitations of generative AI in software architecture.

The SAGAI 2026 Workshop is co-located with the 23rd IEEE International Conference on Software Architecture (ICSA'26) in Amsterdam (Netherlands), and will take place in a date to be defined between June 22 and 23, 2026.

Event details

Location

Amsterdam (Netherlands) -- co-located with ICSA'26

Date

June 22, 2026 - June 23, 2026

Tabbed contents

Expand all Close all

CALL FOR PAPERS

SAGAI's second edition aims to contribute to the establishment of a community of researchers focused on exploring novel ways of using generative AI to improve both development time and runtime aspects of software architectures. To achieve this, we have the following specific objectives:

To provide a forum for scientists and practitioners within the software architecture community to reflect on the potential and limitations of generative AI in software architecture;
To disseminate early results in the field of generative AI for software architecture;
To explore how generative AI can support different audiences (e.g., software architects, developers, requirements engineers, and end users) across architecture activities (e.g., identification of architecture-significant requirements, architectural design, evaluation, implementation, and governance).
To stimulate the investigation of generative AI at runtime in software architectures to address quality attributes such as adaptability, fault tolerance, interoperability, operability, and recoverability, among others.

TOPICS OF INTEREST

GenAI@DT
- Approaches to use generative AI in architecture design and evaluation;
- Generative AI to support architecture knowledge management;
- Generative AI to support the elaboration of architecture scenarios descriptions;
- Generative AI to support the elaboration architecture evaluation protocols;
- Integration and interaction of generative AI methods and tools with existing state of the practice tools;
- Improvement of context knowledge used by co-pilots and LLMs in multiple contexts;
- Approaches to use generative AI in modernization of legacy systems;
- Experiences and ideas on teaching generative AI techniques to software architects;
GenAI@RT
- Architectures to use generative AI at runtime to implement functional requirements;
- Approaches to use generative AI at runtime to address quality requirements;
- Tactics to deal with the non-deterministic character of generative AI to allow for effective and efficient solutions at runtime.

TYPES OF CONTRIBUTION

Full papers: complete research approaches and industry experiences (max. 8 pages).
Short papers: ongoing research initiatives with early results, argued positions, and emerging novel ideas (max. 6 pages).

Submissions proceed via EasyChair.

All submissions must adhere to the IEEE Template for conference proceedings.

PROCEEDINGS

All accepted papers will appear in the ICSA 2026 Companion proceedings.

IMPORTANT DATES

Submission: ~~Feb 13, 2026~~ Feb 20, 2026
Notification: Mar 13, 2026
Camera-ready: Mar 27, 2026

All deadlines are 23:59 AoE.

Workshop date: Jun 22 or 23, 2026 (tbd)

COMMITTEE

ORGANIZING COMMITTEE

Dr. Rodrigo Falcão (Fraunhofer IESE, Kaiserslautern, Germany)
Prof. Dr. Rafael Capilla (Universidad Rey Juan Carlos, Madrid, Spain)
Dr. Frank Elberzhager (Fraunhofer IESE, Kaiserslautern, Germany)
Dr. Pablo Antonino (Fraunhofer IESE, Kaiserslautern, Germany)
Dr. Ivan Compagnucci (Gran Sasso Science Institute, Italy)

PROGRAM COMMITTEE

Eduardo Almeida (Federal University of Bahia, Brazil)
Steffen Becker (University of Stuttgart, Germany)
Klara Borowa (Politechnika Warszawska, Polen)
Jan Bosch (Chalmers University of Technology, Sweden)
Humberto Cervantes (Universidad Autónoma Metropolitana, Mexico)
Andrés Díaz-Pace (Universidad Nacional del Centro de la Provincia de Buenos Aires , Argentina)
Helena Holmström (Malmö University, Sweden)
Jasmin Jahić (University of Cambridge, UK)
Rick Kazman (University of Hawaiʻi, USA)
Michael Kläs (Fraunhofer IESE, Germany)
Jens Knodel (Caruso Dataplace, Germany)
Yue Liu (Australian National University, Australia)
Henry Muccini (University of L'Aquila, Italy)
Matthias Naab (Full Flamingo, Germany)
Patrizio Pelliccione (Gran Sasso Science Institute)
Ralf Reussner (Karlsruher Institut für Technologie, Germany)
Santiago Rey (Universitat Politècnica de Catalunya, Spain)
Maria-Teresa Rossi (Gran Sasso Science Institute, Italy)
Julien Siebert (Fraunhofer IESE, Germany)
Karthik Vaidhyanathan (IIIT Hyderabad, India)
Stefan Wagner (Technical University of Munich, Germany)
Boming Xia (Adelaide University, Australia)
Uwe Zdun (University of Vienna, Austria)

Program

09:00	Intro	Welcome and intro from SAGAI OC
09:30	Keynote	Anton Jansen: “Change”
10:30	Coffee break
11:00	GenAI for assisting software design	Architecture Without Architects: How AI Coding Agents Shape Software Architecture Phongsakon Mark Konrad, Tim Lukas Adam, Riccardo Terrenzi and Serkan Ayvaz
		Designing Adaptive Digital Nudging Systems with LLM-Driven Reasoning Tiziano Santilli, Mina Alipour and Mahyar Tourchi Moghaddam
		Bridging Formal Syntax and LLM Semantics: Extracting Knowledge Graphs for Legacy Code Understanding Henrik Thillmann, Bernhard Rumpe and Andreas Biesdorf
		Towards an LLM-Powered Expert System for AAS-based Product Digital Twin Development Quang-Duy Nguyen, Kunal Suri and Guéréguin Der Sylvestre Sidibe
12:30	Lunch break
13:30	GenAI for addressing quality requirements	Generative AI in Safety Engineering: Transforming HARA Artifacts into DDI Models Pascal Gerber, Marc Lorenz, Joshua Frey, Jan Reich, Markus Schweizer and Josef Kolatschek.
		GARMA: Generative Architectural Resource Demand Estimation for Microservice Applications Maximilian Hummel, Dominik Fuchß, Sophie Corallo, Nathan Hagel, Minakshi Kaushik, Jan Keim, Heiko Koziolek and Ralf Reussner
		SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability Oliver Larsen and Mahyar Tourchi Moghaddam
		Towards Leveraging LLMs to Generate Abstract Penetration Test Cases from Software Architecture Mahdi Jafari, Rahul Sharma, Sami Naim, Christopher Gerking and Ralf Reussner
15:00	Coffee break
15:30	Prompting strategies for software architecture	Automating Domain-Driven Design: Experience with a Prompting Framework Tobias Eisenreich, Husein Jusic and Stefan Wagner
15:30	Prompting strategies for software architecture	Reliability of Large Language Models for Design Synthesis: An Empirical Study of Variance, Prompt Sensitivity, and Method Scaffolding Rabia Iftikhar and Andreas Rausch
16:10	Conclusion	Best paper award, discussion of workshop results, and final remarks