MDE Intelligence

Theme & Goals

Artificial Intelligence (AI) has become part of everyone's life. It is used by companies to exploit the information they collect to improve the products and/or services they offer and, wanted or unwanted, it is present in almost every device around us. Lately, AI is also impacting all aspects of the system and software development lifecycle, from their upfront specification to their design, testing, deployment and maintenance, with the main goal of helping engineers produce systems and software faster and with better quality while being able to handle ever more complex systems and software.

There is no doubt that MDE has been a means to tame until now part of this complexity. However, its adoption by industry still relies on their capacity to manage the underlying methodological changes, including among other things the adoption of new tools. To go one step further, we believe there is a clear need for AI-empowered MDE, which will push the limits of "classic" MDE and provide the right techniques to develop the next generation of highly complex model-based system and software systems engineers will have to design tomorrow.

This workshop provides a forum to discuss, study and explore the opportunities and challenges raised by the integration of AI and MDE.

We would like to address topics such as how to choose, evaluate and adapt AI techniques to Model-Driven Engineering as a way to improve current system and software modeling and generation processes in order to increase the benefits and reduce the costs of adopting MDE. We believe that AI artifacts will empower MDE tools and hence boost the advantages and adoption of MDE at the industry level.

At the same time, AI is software — and complex software, in fact. We therefore also believe that such an AI-powered MDE approach will benefit the design of AI artifacts themselves, especially when facing the challenge of designing trustworthy AI software.

Last but not least, although AI is the most popular branch of computer science to create and simulate intelligence, we also believe that any kind of technique that provides human cognitive capabilities and helps create intelligent software is within the scope of this workshop. Examples include knowledge representation techniques and ontologies that can be useful on their own or support other kinds of AI techniques.

This year, MDE Intelligence adopts the special theme “Assessing the Performance of MDE Intelligence Approaches”, inviting contributions that advance systematic, rigorous, and standardized evaluation practices for intelligent modeling systems.

Call for Papers

Model-driven engineering (MDE) and artificial intelligence (AI) are two separate fields in computer science that can clearly benefit from cross-pollination and collaboration. There are at least two ways in which such integration — which we call MDE Intelligence — can manifest:

Artificial Intelligence for MDE

MDE can benefit from integrating AI concepts and ideas to increase its power: flexibility, user experience, quality, etc. For example, using model transformations through search-based approaches, or by increasing the ability to abstract from partially formed, manual sketches into fully-shaped and formally specified meta-models and editors.

MDE for Artificial Intelligence

AI is software, and as such, it can benefit from integrating concepts and ideas from MDE that have been proven to improve software development. For example, using domain-specific languages allows domain experts to directly express and manipulate their problems while providing an auditable conversion pipeline. Together this can improve trust in and safety of AI technologies. Similarly, MDE technologies can contribute to the goal of fair and explainable AI.

---

TOPICS

Topics of interest for the workshop include, but are not limited to:

AI for MDE

• Application of foundation models (FM), large language models (LLMs), small language models (SLMs), Generative AI, and machine learning to modelling problems;
• Enhanced prompt engineering techniques for generating reliable modeling artifacts;
• Machine learning and Generative AI for (meta-heuristic) search, (meta)models, concrete syntax, model transformations, etc.;
• AI planning applied to (meta-)modelling and model management;
• AI-supported modelling (e.g., bots, recommenders, UI adaptation, etc.);
• Model inferencers and automatic, dataset-based model generators;
• Self-adapting code generators;
• Semantic reasoning, knowledge graphs, or domain-specific ontologies;
• AI-supported model-based digital twins;
• Probabilistic, descriptive or predictive models;
• AI techniques for data, process, and model mining and categorisation;
• Natural language processing applied to modelling, including Large Language Models and Generative AI;
• Reinforcement learning to optimize modelling tasks;
• Generation of synthetic yet reliable modeling artifacts leveraging AI, ML, and foundation models;
• Data quality and privacy issues in AI for MDE;
• Ethical aspects on the application of AI to modeling (responsibility, fairness, bias, etc.).

MDE for AI

• Domain-specific modelling approaches for AI planning, machine learning, agent-based modelling, etc.;
• Model-driven processes for AI system development;
• MDE techniques for explainable and fair AI;
• Using models for knowledge representation;
• Code generation for AI libraries and platforms;
• Architectural languages for AI-enhanced systems;
• MDE for federated learning;
• Model-based testing/analysis of AI components;
• MDE techniques for prompt engineering.

General Topics in MDE Intelligence

• AI in teaching MDE;
• AI for MDE UX;
• Tools, frameworks, modeling standards;
• Encoding conceptual models for AI;
• Datasets for MDE Intelligence;
• Experience reports, case studies, and empirical studies;
• Future challenges for MDE Intelligence.

---

SUBMISSIONS

Submissions must adhere to the ACM formatting instructions.

We ask for two types of contributions:

• 1) Research papers: 10 pages
• 2) Extended abstracts: 5 pages

Page limits include references. Submissions must be uploaded through EasyChair.

All submissions will follow a single-blind review process where each paper will be reviewed by at least three members of the program committee. They will value the relevance and interest for discussions that will take place at the workshop. Accepted papers will be published in the joint workshop proceedings published by ACM.

Papers submitted to MDE Intelligence must not be under review or submitted for review elsewhere whilst under consideration for MDE Intelligence. Contravention of this concurrent submission policy, as stated explicitly by ACM here, will be deemed as a serious breach of scientific ethics, and appropriate action will be taken in all such cases.

Important update on ACM's new Open Access publishing model for 2026 ACM Conferences!
Starting January 1, 2026, ACM has fully transitioned to Open Access. All ACM publications, including those from ACM-sponsored conferences, will be 100% Open Access. See the MODELS 2026 information on Open Access.
Note for this workshop: Extended abstracts will be covered by a specific agreement with MODELS that will not require the payment of any publication fee.

IMPORTANT DATES

• Abstract submission: June 26, 2026
• Paper submission: July 3, 2026
• Notification: July 31, 2026
• Camera-ready: August 14, 2026
• Workshop: October 4–6, 2026

Program

Full-Day Workshop Schedule

09:15 – 10:30	Session 1: Benchmarks and Evaluators for MDE Intelligence Special Theme
	09:15 – 09:30 Workshop Kickoff / Organization 09:30 – 09:50 How Well Do LLMs Suggest Model-to-Model Mappings? A Multi-Provider Benchmark on Hand-Written ATL Transformations Antonio Bucchiarone, Juri Di Rocco and Alfonso Pierantonio 09:50 – 10:10 Evaluating Embedding Models and Preprocessing for Retrieval of MDE Elements in RAG Systems Julian Roßkothen, David Inca Pilco, Tobias Hey, Clemens Reichmann and Ralf Reussner 10:10 – 10:30 On the Non-Interchangeability of Deterministic and LLM-Based UML Evaluators Giacomo Garaccione, Riccardo Coppola and Luca Ardito
10:30 – 11:00	Break
11:00 – 12:45	Session 2: Generating Valid and Conformant Models
	11:00 – 11:30 Keynote / Invited Talk 11:30 – 11:50 Reliable Generation of Feature Models in the Universal Variability Language using Constrained LLMs Johannes Stümpfle, Fethi Tunc, Nasser Jazdi and Michael Weyrich 11:50 – 12:10 Privacy Policy Modeling using Metamodel-Guided LLMs Faezeh Siavashi, Kyanna Dagenais, Ayush Patel and Richard Paige 12:10 – 12:30 From Informal to Conformant Models: Benchmarking Vision-Language Models for UML Generation Cecilia Eklund, Tom Jonsson, Riccardo Rubei and Alessio Bucaioni 12:30 – 12:45 Assessing the Impact of MCP-Augmented LLMs in MDE Tasks: A Quantitative Comparative Evaluation Framework on Fault Tree Modeling and Analysis Through Petri Nets Extended Abstract Filippo Sciammacca, Niccolò Menghini, Nicolò Pollini, Marco Becattini and Enrico Vicario
13:00 – 14:30	Lunch Break
14:30 – 15:45	Session 3: Modeling AI Systems and Processes MDE for AI
	14:30 – 14:50 A Model-Driven Formalization of Prompt Patterns Vennila Sooben and Eugene Syriani 14:50 – 15:10 PRISM: a Modeling Language for Multi-Agent System Interactions in AI-Native Software Engineering Konsta Kalliokoski, François Christophe, Henri Kärkkäinen, Iikka Hämäläinen, Md Mahade Hasan, Md Toufique Hasan, Zheying Zhang, Pekka Abrahamsson and Tommi Mikkonen 15:10 – 15:25 On the Nature of AI Development Processes: Between Recipes and Cooking, Bridging Static Models and Dynamic Enactments Extended Abstract Razan Abualsaud, Hanh Nhi Tran and Ileana Ober 15:25 – 15:45 Beyond Syntax: Method-Compliant AI Assistance for Low-Resource Modeling Languages Sokhna Amar, Maged Elaasar and Sambit Bhattacharya
15:45 – 16:15	Break
16:15 – 17:30	Session 4: Agentic and Tool-Augmented Modeling
	16:15 – 16:30 MagicChat: An In-Tool AI Agent for Industrial Model-Based Engineering in MagicDraw Extended Abstract Rohit Gupta, Nikolaus Regnat and Ambra Calà 16:30 – 16:45 An Agentic LLM-based Environment for Interactive Domain Knowledge Elicitation and Metamodeling Extended Abstract Zakaria Hachm, Alfonso Pierantonio, Davide Di Ruscio, Théo Le Calvar, Massimo Tisi and Hugo Bruneliere 16:45 – 17:00 From Code to Low-Code: An LLM-Driven Pipeline for Lifting Code Clones into Reusable Abstractions Extended Abstract Raphael Zefferer, Bernhard Schenkenfelder and Stefan Wagner 17:00 – 17:30 Lightning Talks / Closing Words

Committees

ORGANIZING COMMITTEE

PROGRAM COMMITTEE

• Syed Juned Ali (TU Wien, Austria)
• Maryam Alshehhi (McGill University, Canada)
• Colin Atkinson (University of Mannheim, Germany)
• Aren A. Babikian (University of Toronto, Canada)
• Antonio Bucchiarone (Università degli Studi dell'Aquila, Italy)
• Thomas Buchmann (Hof University of Applied Sciences, Germany)
• Robert Clarisó (Universitat Oberta de Catalunya, Spain)
• Juan de Lara (Universidad Autónoma de Madrid, Spain)
• Kevin Delcourt (IRIT, France)
• Davide Di Ruscio (Università degli Studi dell'Aquila, Italy)
• Mattia Fumagalli (Free University of Bozen-Bolzano, Italy)
• Antonio Garmendia (Universidad Autónoma de Madrid, Spain)
• Stefan Klikovits (Johannes Kepler University Linz, Austria)
• Dimitris Kolovos (University of York, United Kingdom)
• Jens Kosiol (Philipps-Universität Marburg, Germany)
• Kevin Lano (King's College London, United Kingdom)
• Ana Cristina Marcén (Universidad San Jorge, Spain)
• Judith Michael (Universität Regensburg, Germany)
• Gunter Mussbacher (McGill University, Canada)
• Vittoriano Muttillo (University of L'Aquila, Italy)
• Phuong T. Nguyen (University of L'Aquila, Italy)
• James Pontes Miranda (CEA, France)
• José Raúl Romero (University of Cordoba, Spain)
• Riccardo Rubei (Mälardalen University, Sweden)
• Adrian Rutle (Western Norway University of Applied Sciences, Norway)
• Jonathan Silva Mercado (University of Luxembourg, Luxembourg)
• Daniel Strüber (University of Gothenburg, Sweden; Radboud University Nijmegen, Netherlands)
• Eugene Syriani (University of Montreal, Canada)
• Gabriele Taentzer (Philipps-Universität Marburg, Germany)
• Marina Tropmann-Frick (Hamburg University of Applied Sciences, Germany)
• Steffen Zschaler (King's College London, United Kingdom)