{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:47:42Z","timestamp":1780501662797,"version":"3.54.1"},"reference-count":60,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>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\u2019s 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\u2019 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\u2019s 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.<\/jats:p>","DOI":"10.3390\/info16090809","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T14:10:19Z","timestamp":1758118219000},"page":"809","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["BPMN-Based Design of Multi-Agent Systems: Personalized Language Learning Workflow Automation with RAG-Enhanced Knowledge Access"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1282-2820","authenticated-orcid":false,"given":"Hedi","family":"Tebourbi","sequence":"first","affiliation":[{"name":"Faculty of Science, Technology and Medicine, University of Luxembourg, Belval Campus, 2 Place de l\u2019Universit\u00e9, L-4365 Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6722-4008","authenticated-orcid":false,"given":"Sana","family":"Nouzri","sequence":"additional","affiliation":[{"name":"Faculty of Science, Technology and Medicine, University of Luxembourg, Belval Campus, 2 Place de l\u2019Universit\u00e9, L-4365 Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6772-6135","authenticated-orcid":false,"given":"Yazan","family":"Mualla","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard (UTBM), CIAD UR 7533, F-90010 Belfort, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3053-8895","authenticated-orcid":false,"given":"Meryem","family":"El Fatimi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Science Semlalia, Cadi Ayyad University, Bd Abdelkrim Al Khattabi, Marrakech 40000, Morocco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7784-6176","authenticated-orcid":false,"given":"Amro","family":"Najjar","sequence":"additional","affiliation":[{"name":"Luxembourg Institute of Science and Technology, L-4362 Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4443-0542","authenticated-orcid":false,"given":"Abdeljalil","family":"Abbas-Turki","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard (UTBM), CIAD UR 7533, F-90010 Belfort, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5071-1287","authenticated-orcid":false,"given":"Mahjoub","family":"Dridi","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Universit\u00e9 de Technologie de Belfort-Montb\u00e9liard (UTBM), CIAD UR 7533, F-90010 Belfort, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Belda-Medina, J., and Calvo-Ferrer, J.R. (2022). Using Chatbots as AI Conversational Partners in Language Learning. Appl. Sci., 12.","DOI":"10.3390\/app12178427"},{"key":"ref_2","unstructured":"Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., and Qin, B. (2023). A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, M.H., and Ye, S.X. (2022). Extending repair in peer interaction: A conversation analytic study. Front. Psychol., 13.","DOI":"10.3389\/fpsyg.2022.926842"},{"key":"ref_4","unstructured":"Huang, Y., Qin, Z., and Liu, W. (2023, January 9\u201314). Hallucinations in Large Language Models: Challenges and Mitigation Strategies. Proceedings of the ACL, Toronto, On, Canada."},{"key":"ref_5","unstructured":"Statistics Portal, Luxembourg (2025, June 22). Linguistic Diversity on the Rise. Available online: https:\/\/statistiques.public.lu\/en\/recensement\/diversite-linguistique.html."},{"key":"ref_6","unstructured":"Statistics Portal, Luxembourg (2025, June 22). Nationalities. Available online: https:\/\/statistiques.public.lu\/en\/recensement\/nationalites.html."},{"key":"ref_7","unstructured":"Halder, S., Meyer, T., and Schmidt, L. (2024, January 20\u201325). Challenges in NLP for Low-Resource Languages: The Case of Luxembourgish. Proceedings of the LREC, Torino, Italia."},{"key":"ref_8","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., and Sutskever, I. (2023, January 23\u201329). Robust Speech Recognition via Large-Scale Weak Supervision. Proceedings of the 40th International Conference on Machine Learning (PMLR), Honolulu, HI, USA."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ju-Zaoravi, Y., and Lee, S.X. (2023). Online language learning in participatory culture: Digital pedagogy practices in the post-pandemic era. Educ. Sci., 13.","DOI":"10.3390\/educsci13121217"},{"key":"ref_10","first-page":"124","article-title":"L2 teacher support and positive L2 academic emotions: The mediating role of self-efficacy","volume":"51","author":"Xie","year":"2022","journal-title":"J. Psycholinguist. Res."},{"key":"ref_11","unstructured":"Lothritz, C. (2023). NLP De Luxe\u2014Challenges for Natural Language Processing in Luxembourg. [Doctoral Thesis, University of Luxembourg]."},{"key":"ref_12","first-page":"103","article-title":"Exploring the capabilities and possible applications of large language models for education. In Proceedings of the 2023 21st International Conference on Emerging eLearning Technologies and Applications (ICETA), Stary Smokovec, Slovakia, 26\u201327 October 2023; pp. 91\u201398","volume":"68","author":"Hasin","year":"2025","journal-title":"IEEE Trans. Educ."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Abedi, M., Alshybani, I., Shahadat, M., and Murillo, M. (2023). Beyond traditional teaching: The potential of large language models and chatbots in graduate engineering education. arXiv.","DOI":"10.32388\/MD04B0.2"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/TE.2024.3467912","article-title":"An LLM-driven chatbot in higher education for databases and information systems","volume":"68","author":"Neumann","year":"2025","journal-title":"IEEE Trans. Educ."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Van Der Peijl, E., Najjar, A., Mualla, Y., Bourscheid, T.J., Spinola-Elias, Y., Karpati, D., and Nouzri, S. (2021, January 3\u20137). Toward XAI & human synergies to explain the history of art:The smart photobooth project. Proceedings of the International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems, Virtual Event.","DOI":"10.1007\/978-3-030-82017-6_13"},{"key":"ref_16","unstructured":"Tebourbi, H., Nouzri, S., Mualla, Y., and Najjar, A. (2025, January 19\u201323). Personalized Language Learning: A Multi-Agent System Leveraging LLMs for Teaching Luxembourgish. Proceedings of the AAMAS 2025, Detroit, MI, USA. Available online: https:\/\/www.ifaamas.org\/Proceedings\/aamas2025\/pdfs\/p3032.pdf."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Arisaka, R., Sanchez-Anguix, V., Stein, S., Aydo\u011fan, R., van der Torre, L., and Ito, T. (2025). Beyond Chatbots: Enhancing Luxembourgish Language Learning Through Multi-agent Systems and Large Language Model. Proceedings of the PRIMA 2024: Principles and Practice of Multi-Agent Systems, Kyoto, Japan, 18\u201324 November 2024, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-031-77367-9"},{"key":"ref_18","unstructured":"Object Management Group (2025, June 22). Business Process Model and Notation (BPMN). Available online: https:\/\/www.bpmn.org."},{"key":"ref_19","unstructured":"Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W., and Rockt\u00e4schel, T. (2020, January 6\u201312). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Proceedings of the NeurIPS, Virtual."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Picard, A., Mualla, Y., Gechter, F., and Galland, S. (2023, January 26\u201328). Human-computer interaction and explainability: Intersection and terminology. Proceedings of the World Conference on Explainable Artificial Intelligence, Lisboa, Portugal.","DOI":"10.1007\/978-3-031-44067-0_12"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/3236009","article-title":"A survey of methods for explaining black box models","volume":"51","author":"Guidotti","year":"2019","journal-title":"Acm Comput. Surv. (Csur)"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103573","DOI":"10.1016\/j.artint.2021.103573","article-title":"The quest of parsimonious XAI: A human-agent architecture for explanation formulation","volume":"302","author":"Mualla","year":"2022","journal-title":"Artif. Intell."},{"key":"ref_23","unstructured":"Hemmer, P., Schemmer, M., V\u00f6ssing, M., and K\u00fchl, N. (2021, January 12\u201314). Human-AI complementarity in hybrid intelligence systems: A structured literature review. Proceedings of the 25th Pacific Asia Conference on Information Systems (PACIS), Dubai, United Arab Emirates."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Glass, A., McGuinness, D.L., and Wolverton, M. (2008, January 13\u201316). Toward establishing trust in adaptive agents. Proceedings of the 13th International Conference on Intelligent User Interfaces, Gran Canaria, Spain.","DOI":"10.1145\/1378773.1378804"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mualla, Y., Tchappi, I.H., Najjar, A., Kampik, T., Galland, S., and Nicolle, C. (2020, January 22\u201324). Human-agent explainability: An experimental case study on the filtering of explanations. Proceedings of the 12th International Conference on Agents and Artificial Intelligence, Valletta, Malta.","DOI":"10.5220\/0009382903780385"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Liao, Q.V., Gruen, D., and Miller, S. (2020, January 25\u201330). Questioning the AI: Informing design practices for explainable AI user experiences. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA.","DOI":"10.1145\/3313831.3376590"},{"key":"ref_27","unstructured":"Mualla, Y. (2020). Explaining the Behavior of Remote Robots to Humans: An Agent-Based Approach. [Ph.D. Dissertation, Universit\u00e9 Bourgogne Franche-Comt\u00e9]. Available online: https:\/\/tel.archives-ouvertes.fr\/tel-03162833."},{"key":"ref_28","unstructured":"Gunning, D. (2025, July 01). Explainable Artificial Intelligence (XAI). Defense Advanced Research Projects Agency (DARPA). Available online: https:\/\/www.darpa.mil\/program\/explainable-artificial-intelligence."},{"key":"ref_29","unstructured":"Biran, O., and Cotton, C. (2017, January 19\u201325). Explanation and justification in machine learning: A survey. Proceedings of the IJCAI-17 Workshop on Explainable AI (XAI), Melbourne, Australia."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Contreras, V., Marini, N., Fanda, L., Manzo, G., Mualla, Y., Calbimonte, J.-P., Schumacher, M., and Calvaresi, D. (2022). A dexire for extracting propositional rules from neural networks via binarization. Electronics, 11.","DOI":"10.3390\/electronics11244171"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Schutz, P.A., and Muis, K.R. (2023). Intelligent Tutoring Systems: How computers achieve learning gains that rival human tutors. Handbook of Educational Psychology, American Psychological Association. [4th ed.].","DOI":"10.4324\/9780429433726"},{"key":"ref_32","first-page":"104","article-title":"BPMN for Educational Process Modeling: A Systematic Approach","volume":"198","author":"Smith","year":"2023","journal-title":"Comput. Educ."},{"key":"ref_33","first-page":"6543","article-title":"Applying BPMN to Adaptive E-Learning Path Modeling: A Case Study","volume":"28","author":"Costa","year":"2023","journal-title":"Educ. Inf. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ait, A., C\u00e1novas Izquierdo, J.L., and Cabot, J. (2024). Towards Modeling Human\u2013Agentic Collaborative Workflows: A BPMN Extension. arXiv.","DOI":"10.1007\/978-3-032-04190-6_22"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/s40561-023-00259-5","article-title":"A BPM-based approach for ensuring an agile and adaptive learning process","volume":"10","author":"Bergaoui","year":"2023","journal-title":"Smart Learn. Environ."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1017\/S0269888900008122","article-title":"Intelligent Agents: Theory and Practice","volume":"10","author":"Wooldridge","year":"1995","journal-title":"Knowl. Eng. Rev."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ivanova, T., Terzieva, V., and Todorova, K. (2021, January 28\u201329). An Agent-Oriented Architecture For Strategy-Based Personalized E-Learning. Proceedings of the 2021 Big Data, Knowledge and Control Systems Engineering (BdKCSE), Sofia, Bulgaria.","DOI":"10.1109\/BdKCSE53180.2021.9627260"},{"key":"ref_38","unstructured":"Microsoft Research (2025, July 01). AutoGen: Enable Next-Gen Large Language Model Applications. Available online: https:\/\/github.com\/microsoft\/autogen."},{"key":"ref_39","unstructured":"LangChain Inc (2025, July 01). LangGraph: Building Stateful Multi-Agent Applications. Available online: https:\/\/langchain.com\/langgraph."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Chowdhury, S.P., Zouhar, V., and Sachan, M. (2024). AutoTutor Meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails. arXiv.","DOI":"10.1145\/3657604.3662041"},{"key":"ref_41","first-page":"156","article-title":"RAG Applications in Educational AI: Reducing Hallucinations and Improving Accuracy","volume":"11","author":"Wang","year":"2024","journal-title":"J. AI Educ."},{"key":"ref_42","unstructured":"Oche, A.J., Folashade, A.G., Ghosal, T., and Biswas, A. (2024). A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions. arXiv."},{"key":"ref_43","unstructured":"Niu, M., Li, H., Shi, J., Haddadi, H., and Mo, F. (2024). Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval. arXiv."},{"key":"ref_44","first-page":"245","article-title":"Addressing Hallucinations in Educational AI: A Critical Analysis","volume":"33","author":"Rzepka","year":"2023","journal-title":"Int. J. AI Educ."},{"key":"ref_45","unstructured":"Duolingo Inc (2025, June 22). Language Learning Platform: Features and Limitations. Available online: https:\/\/www.duolingo.com."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Scarlatos, A., Liu, N., Lee, J., Baraniuk, R., and Lan, A. (2024). Training LLM-Based Tutors to Improve Student Learning Outcomes in Dialogues. arXiv.","DOI":"10.1007\/978-3-031-98414-3_18"},{"key":"ref_47","unstructured":"Lavergne, T., Urvoy, T., and Yvon, F. (2022, January 20\u201325). NLP Resources for Luxembourgish: Current State and Future Directions. Proceedings of the LREC, Marseille, France."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, E., Ott, M., Zettlemoyer, L., and Stoyanov, V. (2020, January 5\u201310). Unsupervised Cross-lingual Representation Learning at Scale. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref_49","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the NAACL-HLT 2019, Minneapolis, MN, USA."},{"key":"ref_50","unstructured":"Plum, A., Ranasinghe, T., and Purschke, C. (2025, January 19). Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy. Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2025), Abu Dhabi, United Arab Emirates."},{"key":"ref_51","unstructured":"Lutgen, A.-M., Plum, A., Purschke, C., and Plank, B. (2025, January 19). Neural Text Normalization for Luxembourgish Using Real-Life Variation Data. Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2025), Abu Dhabi, United Arab Emirates."},{"key":"ref_52","unstructured":"Gilles, P., Hosseini-Kivanani, N., and Ayit\u00e9 Hillah, L.E. (2023, January 7\u201311). ASRLUX: Automatic Speech Recognition for the Low-Resource Language Luxembourgish. Proceedings of the 20th International Congress of Phonetic Sciences (ICPhS 2023), Prague, Czech Republic."},{"key":"ref_53","unstructured":"Plum, A., D\u00f6hmer, C., Milano, E., Lutgen, A.-M., and Purschke, C. (2024). LuxBank: The First Universal Dependency Treebank for Luxembourgish. arXiv."},{"key":"ref_54","unstructured":"LangChain Inc (2025, July 01). LangSmith: Interactive Tooling for Explainable LLM Workflows. Available online: https:\/\/langchain.com\/langsmith."},{"key":"ref_55","unstructured":"LangChain Inc (2025, July 01). LangChain: Building Applications with LLMs Through Composable Chains and Tools. Available online: https:\/\/www.langchain.com."},{"key":"ref_56","first-page":"28","article-title":"Comparing Different Approaches for Automatic Pronunciation Error Detection","volume":"113","author":"Strik","year":"2019","journal-title":"Speech Commun."},{"key":"ref_57","unstructured":"Coqui Inc (2025, July 01). Coqui TTS: VITS-Based Text-to-Speech Models. Available online: https:\/\/coqui.ai."},{"key":"ref_58","unstructured":"OpenAI (2025, July 01). Whisper: Robust Speech Recognition via Large-Scale Weak Supervision. Available online: https:\/\/openai.com\/research\/whisper."},{"key":"ref_59","unstructured":"OpenAI (2025, July 01). GPT-4 with Vision: Multimodal Large Language Models. Available online: https:\/\/platform.openai.com\/docs\/guides\/vision."},{"key":"ref_60","unstructured":"Chroma Inc (2025, July 01). Chroma: Open-Source Embeddings Database for AI Applications. Available online: https:\/\/www.trychroma.com."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/809\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:47:20Z","timestamp":1760035640000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":60,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["info16090809"],"URL":"https:\/\/doi.org\/10.3390\/info16090809","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]}}}