BPMN-Based Design of Multi-Agent Systems: Personalized Language Learning Workflow Automation with RAG-Enhanced Knowledge Access †
Kaydedildi:
| Yayımlandı: | Information vol. 16, no. 9 (2025), p. 809-841 |
|---|---|
| Yazar: | |
| Diğer Yazarlar: | , , , , , |
| Baskı/Yayın Bilgisi: |
MDPI AG
|
| Konular: | |
| Online Erişim: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3254540524 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2078-2489 | ||
| 024 | 7 | |a 10.3390/info16090809 |2 doi | |
| 035 | |a 3254540524 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231474 |2 nlm | ||
| 100 | 1 | |a Tebourbi Hedi |u Faculty of Science, Technology and Medicine, University of Luxembourg, Belval Campus, 2 Place de l’Université, L-4365 Esch-sur-Alzette, Luxembourg | |
| 245 | 1 | |a BPMN-Based Design of Multi-Agent Systems: Personalized Language Learning Workflow Automation with RAG-Enhanced Knowledge Access † | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a The intersection of Artificial Intelligence (AI) and education is revolutionizing learning and teaching in this digital era, with Generative AI and large language models (LLMs) providing even greater possibilities for the future. The digital transformation of language education demands innovative approaches that combine pedagogical rigor with explainable AI (XAI) principles, particularly for low-resource languages. This paper presents a novel methodology that integrates Business Process Model and Notation (BPMN) with Multi-Agent Systems (MAS) to create transparent, workflow-driven language tutors. Our approach uniquely embeds XAI through three mechanisms: (1) BPMN’s visual formalism that makes agent decision-making auditable, (2) Retrieval-Augmented Generation (RAG) with verifiable knowledge provenance from textbooks of the National Institute of Languages of Luxembourg, and (3) human-in-the-loop validation of both content and pedagogical sequencing. To ensure realism in learner interaction, we integrate speech-to-text and text-to-speech technologies, creating an immersive, human-like learning environment. The system simulates intelligent tutoring through agents’ collaboration and dynamic adaptation to learner progress. We demonstrate this framework through a Luxembourgish language learning platform where specialized agents (Conversational, Reading, Listening, QA, and Grammar) operate within BPMN-modeled workflows. The system achieves high response faithfulness (0.82) and relevance (0.85) according to RAGA metrics, while speech integration using Whisper STT and Coqui TTS enables immersive practice. Evaluation with learners showed 85.8% satisfaction with contextual responses and 71.4% engagement rates, confirming the effectiveness of our process-driven approach. This work advances AI-powered language education by showing how formal process modeling can create pedagogically coherent and explainable tutoring systems. The architecture’s modularity supports extension to other low-resource languages while maintaining the transparency critical for educational trust. Future work will expand curriculum coverage and develop teacher-facing dashboards to further improve explainability. | |
| 651 | 4 | |a Luxembourg | |
| 653 | |a Modularity | ||
| 653 | |a Language acquisition | ||
| 653 | |a Collaboration | ||
| 653 | |a Large language models | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Text-to-speech | ||
| 653 | |a Education | ||
| 653 | |a Formalism | ||
| 653 | |a Language instruction | ||
| 653 | |a Decision making | ||
| 653 | |a Workflow | ||
| 653 | |a Generative artificial intelligence | ||
| 653 | |a Knowledge management | ||
| 653 | |a Business process engineering | ||
| 653 | |a Multiagent systems | ||
| 653 | |a Language modeling | ||
| 653 | |a Explainable artificial intelligence | ||
| 653 | |a Learning environment | ||
| 653 | |a Luxembourgish | ||
| 653 | |a Chatbots | ||
| 653 | |a Speech recognition | ||
| 653 | |a Tutoring | ||
| 653 | |a Transparency | ||
| 653 | |a Automation | ||
| 653 | |a Conversation | ||
| 653 | |a Models | ||
| 653 | |a Textbooks | ||
| 653 | |a Organizational effectiveness | ||
| 653 | |a Speech | ||
| 653 | |a Teaching | ||
| 653 | |a Teachers | ||
| 653 | |a Languages | ||
| 653 | |a Curricula | ||
| 653 | |a Responses | ||
| 653 | |a Learning | ||
| 653 | |a Agents | ||
| 653 | |a Retrieval | ||
| 653 | |a Transformation | ||
| 653 | |a Language shift | ||
| 653 | |a Satisfaction | ||
| 653 | |a Language | ||
| 700 | 1 | |a Nouzri Sana |u Faculty of Science, Technology and Medicine, University of Luxembourg, Belval Campus, 2 Place de l’Université, L-4365 Esch-sur-Alzette, Luxembourg | |
| 700 | 1 | |a Yazan, Mualla |u Faculty of Computer Science, Université de Technologie de Belfort-Montbéliard (UTBM), CIAD UR 7533, F-90010 Belfort, France; abdeljalil.abbas-turki@utbm.fr (A.A.-T.); mahjoub.dridi@utbm.fr (M.D.) | |
| 700 | 1 | |a Meryem, El Fatimi |u Department of Computer Science, Faculty of Science Semlalia, Cadi Ayyad University, Bd Abdelkrim Al Khattabi, Marrakech 40000, Morocco; meryem.elfatimi@uir.ac.ma | |
| 700 | 1 | |a Najjar Amro |u Luxembourg Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg; amro.najjar@list.lu | |
| 700 | 1 | |a Abbas-Turki Abdeljalil |u Faculty of Computer Science, Université de Technologie de Belfort-Montbéliard (UTBM), CIAD UR 7533, F-90010 Belfort, France; abdeljalil.abbas-turki@utbm.fr (A.A.-T.); mahjoub.dridi@utbm.fr (M.D.) | |
| 700 | 1 | |a Dridi Mahjoub |u Faculty of Computer Science, Université de Technologie de Belfort-Montbéliard (UTBM), CIAD UR 7533, F-90010 Belfort, France; abdeljalil.abbas-turki@utbm.fr (A.A.-T.); mahjoub.dridi@utbm.fr (M.D.) | |
| 773 | 0 | |t Information |g vol. 16, no. 9 (2025), p. 809-841 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3254540524/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3254540524/fulltextwithgraphics/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3254540524/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |