BPMN; Language learning; LLMs; MAS; Personalized Adaptive Learning; RAG; Adaptive learning; Business process model and notation; Business process modeling; Chatbots; Language model; Large language model; Multiagent systems (MASs); Personalized adaptive learning; Retrieval-augmented generation; Theoretical Computer Science; Computer Science (all)
Abstract :
[en] The intersection of Artificial Intelligence (AI) and education is transforming learning and teaching, with Generative AI (GenAI) and large language models (LLMs) offering new possibilities. AI and LLMs personalize learning through adaptive study guides, instant feedback, automated grading, and content creation, making resources more accessible and tailored to individual needs. Notably, LLM-based chatbots, such as OpenAI’s ChatGPT, serve as virtual assistants, ideal for language practice. However, these chatbots often limit themselves to teaching vocabulary through role-playing conversations or providing instant feedback based on model-generated content, which may lead to exposure to inaccuracies. This overlooks the holistic nature of Language Learning (LL), which requires pedagogy, effective methods, reliable content, and a supportive teacher-student relationship. Therefore, relying on a single chatbot is inefficient for the entire learning process. In this paper, a Multi-Agent System (MAS) is proposed, where each agent specializes in a specific function, working together to provide personalized, adaptive learning support. This approach breaks down the complex learning process into manageable parts. It employs the Business Process Model and Notation (BPMN), translated into agent-based modeling and LLMs to create dynamic, tailored learning environments. By simulating interactions similar to human tutoring, this model ensures real-time adjustments to meet each student’s evolving needs. Our project aims to address these limitations by using LL books with robust pedagogical resources as primary references. We focus on teaching Luxembourgish, adding complexity to our challenges as it is a low-resource language, ensuring a holistic learning experience. Our approach employs complex LLM workflows as multi-agent collaborations for reading, conversing, listening, and mastering grammar, based on GPT-4o, enhanced by Retrieval-Augmented Generation (RAG) and voice recognition features.
Disciplines :
Computer science
Author, co-author :
NOUZRI, Sana ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
EL Fatimi, Meryem; Cadi Ayyad University, Marrakech, Morocco
Guerin, Titouan; Sorbonne University, Paris, France
Othmane, Mahfoud; AI-Robolab/ICR, Computer Science and Communications, University of Luxembourg, Esch-sur-Alzette, Luxembourg
NAJJAR, Amro ; University of Luxembourg > Faculty of Science, Technology and Medicine > Department of Computer Science > Team Leon VAN DER TORRE ; Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg
External co-authors :
yes
Language :
English
Title :
Beyond Chatbots: Enhancing Luxembourgish Language Learning Through Multi-agent Systems and Large Language Model
Publication date :
15 November 2024
Event name :
The 25th International Conference on Principles and Practice of Multi-Agent Systems
Event place :
Kyoto, Japan
Event date :
18-11-2024 => 24-11-2024
By request :
Yes
Main work title :
PRIMA 2024: Principles and Practice of Multi-Agent Systems - 25th International Conference, Proceedings
Editor :
Arisaka, Ryuta
Ito, Takayuki
Publisher :
Springer Science and Business Media Deutschland GmbH
Department of Education, Western Australia: Benefits of Learning a Language. education.wa.edu.au/dl/m9q4gp. Accessed 5 July 2024
Ju-Zaveroni, Y., Lee, S.: Online language learning in participatory culture: digital pedagogy practices in the post-pandemic era. Educ. Sci. 13(12), 1217 (2023). https://doi.org/10.3390/educsci13121217
Center for Educational Innovation: Pedagogy - Diversifying your teaching methods, learning activities, and assignments, University of Minnesota. cei.umn.edu. Accessed 5 July 2024
Belda-Medina, J., Calvo-Ferrer, J.R.: Using chatbots as AI conversational partners in language learning. Appl. Sci. 12(17), 8427 (2022). https://doi.org/10.3390/app12178427
Chen, M.H., Ye, S.X.: Extending repair in peer interaction: a conversation analytic study. Front. Psychol. 13, 926842 (2022). https://doi.org/10.3389/fpsyg.2022.926842
Uspenskyi, S.: How LLM Can Transform Education. Springs (2023). springsapps.com
Ningsih, F.: Classtime.Com as an AI-based testing platform: analysing ESP students’ performances and feedback. J. Lang. Lang. Teach. 11(3) (2023). https://doi.org/10.33394/jollt.v11i3.8286
Dewi, H.K., Rahim, N.A., Putri, R.E., Wardani, T.I., Rumambo, M.G.: The Use of AI (Artificial Intelligence) in English Learning Among University Students: Case Study in English Department, Universitas Airlangga (2021)
Baker, W.: English as a global lingua franca: lingua frankensteinia or intercultural opportunity? In: Mathews-Aydinli, J. (ed.) International Education Exchanges and Intercultural Understanding, pp. 41–58. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-43829-0_4
Google: Gemini Technical Report. Google AI (2023). https://ai.google
Papasalouros, A., Kotis, K., Zangogianni, P., Daradoumis, A.: Educational AI chatbots for content and language integrated learning. Appl. Sci. 12(7), 3239 (2022). https://doi.org/10.3390/app12073239
Petrović, J., Jovanović, M.: The role of chatbots in foreign language learning: the present situation and the future outlook. In: Pap, E. (ed.) Artificial Intelligence: Theory and Applications. SCI, vol. 973, pp. 313–330. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72711-6_17
Strik, H., Truong, K., de Wet, F., Cucchiarini, C.: Comparing different approaches for automatic pronunciation error detection. Speech Commun. 113, 28–39 (2019). sciencedirect.com
NVIDIA: Pushing the Boundaries of Speech Recognition with NeMo and Parakeet ASR Models. developer.nvidia.com. Accessed 2024
Gladia: A Review of the Best ASR Engines and the Models Powering Them in 2024. gladia.io. Accessed 2024
Stanford HAI: AI Will Transform Teaching and Learning. Let’s Get It Right (2024). hai.stanford.edu
Rus, V., Niraula, N.B., D’Mello, S.K., Graesser, A.C.: Recent advances in conversational intelligent tutoring systems. In: AIED (2021)
D’Mello, S.K., Graesser, A.C.: Intelligent tutoring systems: how computers achieve learning gains that rival human tutors. In: Schutz, P., Muis, K.R. (eds.) Handbook of Educational Psychology, vol. 4, pp. 603–629. American Psychological Association, Washington, D.C. (2023)
Ivanova, T., Terzieva, V., Todorova, K.: An agent-oriented architecture for strategy-based personalized e-learning. In: 2021 Big Data, Knowledge and Control Systems Engineering (BdKCSE), pp. 1–8. IEEE (2021)
Vesin, B., Ivanović, M., Klašnja-Milićević, A., Budimac, Z.: Personal assistance agent in programming tutoring system. In: Jezic, G., Howlett, R.J., Jain, L.C. (eds.) Agent and Multi-Agent Systems: Technologies and Applications. SIST, vol. 38, pp. 441–451. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-19728-9_37
Seo, K., Tang, J., Roll, I., Fels, S., Yoon, D.: The impact of artificial intelligence on learner–instructor interaction in online learning. Int. J. Educ. Technol. High. Educ. 18(1), 1–23 (2021). https://doi.org/10.1186/s41239-021-00292-9
Adıgüzel, T., Kaya, M.H., Cansu, F.K.: Revolutionizing education with AI: exploring the transformative potential of ChatGPT. Contemp. Educ. Technol. (2023)
Sajja, R., Sermet, Y., Cikmaz, M., Cwiertny, D., Demir, I.: Artificial intelligence-enabled intelligent assistant for personalized and adaptive learning in higher education. arXiv preprint arXiv:2309.10892 (2023)
Labadze, L., Grigolia, M., Machaidze, L.: Role of AI chatbots in education: systematic literature review. Int. J. Educ. Technol. High. Educ. 20, 56 (2023). https://doi.org/10.1186/s41239-023-00426-1
Aleven, V.: Rule-based cognitive modeling for intelligent tutoring systems. In: Nkambou, R., Bourdeau, J., Mizoguchi, R. (eds.) Advances in Intelligent Tutoring Systems. SCI, vol. 308, pp. 33–62. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-14363-2_3
Sanako Blog: How Effective Are Apps for Language Learning, 21 March 2022. sanako.com. Accessed 2024
Abou-Khalil, V., Flanagan, B., Ogata, H.: Personal vocabulary recommendation to support real life needs. In: Roll, I., McNamara, D., Sosnovsky, S., Luckin, R., Dimitrova, V. (eds.) AIED 2021. LNCS (LNAI), vol. 12749, pp. 18–23. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78270-2_3
Rzepka, N., Simbeck, K., Müller, H.G., Pinkwart, N.: Go with the flow: personalized task sequencing improves online language learning. In: Wang, N., Rebolledo-Mendez, G., Matsuda, N., Santos, O.C., Dimitrova, V. (eds.) AIED 2023. LNCS, vol. 13916, pp. 90–101. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-36272-9_8
Huang, X., Zou, D., Cheng, G., Chen, X., Xie, H.: Trends, research issues and applications of artificial intelligence in language education. Educ. Technol. Soc. 26(1), 112–131 (2023). https://www.jstor.org/stable/48707971
Ebadi, S., Amini, A.: Examining the roles of social presence and human-likeness on Iranian EFL learners’ motivation using artificial intelligence technology: a case of CSIEC chatbot. Interact. Learn. Environ. (2022). https://doi.org/10.1080/10494820.2022.2096638
Leadership Stack: The Limitations of AI: Why Human Intelligence Will Always Have an Edge, 1 June 2023. leadershipstack.com. Accessed 2024
Wei, L.: Artificial intelligence in language instruction: impact on English learning achievement, L2 motivation, and self-regulated learning. Front. Psychol. (2023). https://doi.org/10.3389/fpsyg.2023.1261955
Lux Today: Voice recognition app created for Luxembourgish, 12 December 2022. luxtoday.lu. Accessed 2024
Kannan, S.S., Venkatesh, V.L., Min, B.-C.: Smart-LLM: smart multi-agent robot task planning using large language models. arXiv preprint arXiv:2309.10062 (2023)
Zhang, H., et al.: Building cooperative embodied agents modularly with large language models. In: The Twelfth International Conference on Learning Representations (ICLR) (2024)
Sun, C., Huang, S., Pompili, D.: LLM-based multi-agent reinforcement learning: current and future directions. arXiv preprint, arXiv:2405.11106 (2024)
Liu, Z., Zhang, Y., Li, P., Liu, Y., Yang, D.: Dynamic LLM-agent network: an LLM-agent collaboration framework with agent team optimization. arXiv preprint arXiv:2310.02170 (2023)
Slumbers, O., Mguni, D.H., Shao, K., Wang, J.: Leveraging Large Language Models for Optimized Coordination in Textual Multi-Agent Reinforcement Learning (2023)
