A Multi-Agent Chatbot Architecture for AI-Driven Language Learning
Source abstract
Abstract
Language learners increasingly rely on intelligent digital tools to supplement their learning experiences, yet existing chatbots often provide limited support, lacking adaptability, personalization, or domain-specific intelligence. This study introduces a novel AI-powered multi-agent chatbot architecture designed to support English–Arabic translation and language learning. Developed through a three-phase methodology, offline preparation, real-time deployment, and evaluation, the system employs both retrieval-based and generative AI models, with specialized agents managing tasks such as translation, example retrieval, user translation review, and learning feedback. The chatbot was developed using a hybrid architecture incorporating fine-tuned Generative Pre-trained Transformer (GPT) model, sentence embedding techniques, and similarity evaluation metrics. A user study involving 40 undergraduate students and 4 faculty members evaluated the system across usability, effectiveness, and pedagogical value. Results show that the multi-agent chatbot significantly enhanced learner engagement, provided accurate and contextually appropriate language support, and was positively received by both students and instructors. These findings demonstrate the value of multi-agent design in language learning applications and highlight the potential of AI-driven chatbots as intelligent educational assistants.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Natural Language Processing Techniques · AI in Service Interactions
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information Technology, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi Arabia
School of Computer Science, University of Leeds, Leeds LS2 9JT, UK
Funding
Princess Nourah bint Abdulrahman University Researchers Supporting Project
References (32)
Show source-provided references
1. PNU (2025, September 26). Princess Nourah Bint Abdulrahman University. Available online: https://pnu.edu.sa/en/AboutUniversity/Pages/About.aspx.
2. ELIZA-A computer program for the study of natural language communication between man and machine10.1145/365153.365168 ↗
3. Shum, H.Y., He, X.D., and Li, D. (2018). From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots, Zhejiang University.10.1631/FITEE.1700826 ↗
4. Makhkamova, O., Lee, K.H., Do, K., and Kim, D. (2020, January 19–22). Deep learning-based multi-chatbot broker for q&a improvement of video tutoring assistant. Proceedings of the 2020 IEEE International Conference on Big Data and Smart Computing, BigComp 2020, Busan, South Korea.10.1109/BigComp48618.2020.00-71 ↗
5. Nuruzzaman, M., and Hussain, O.K. (2018, January 12–14). A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks. Proceedings of the 2018 IEEE 15th International Conference on e-Business Engineering, ICEBE 2018, Xi’an, China.10.1109/ICEBE.2018.00019 ↗
6. Qiu, M., Li, F.-L., Wang, S., Gao, X., Chen, Y., Zhao, W., Chen, H., Huang, J., and Chu, W. (2017). AliMe Chat: A Sequence to Sequence and Rerank based Chatbot Engine. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics.10.18653/v1/P17-2079 ↗
7. Serban, I.V., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., Kim, T., Pieper, M., Chandar, S., and Ke, N.R. (2020, December 01). A Deep Reinforcement Learning Chatbot. Available online: http://arxiv.org/abs/1709.02349.
8. Lin, Z., Xu, P., Winata, G.I., Siddique, F.B., Liu, Z., Shin, J., and Fung, P. (2021, January 17). CAiRE: An Empathetic Neural Chatbot. Available online: http://arxiv.org/abs/1907.12108.
9. Hien, H.T., Cuong, P.N., Nam, L.N.H., Nhung, H.L.T.K., and Thang, L.D. (2018). Intelligent assistants in higher-education environments: The FIT-EBOt, a chatbot for administrative and learning support. ACM International Conference Proceeding Series, Association for Computing Machinery.10.1145/3287921.3287937 ↗
10. Yang, S., Wang, Y., and Chu, X. (2020). A Survey of Deep Learning Techniques for Neural Machine Translation. arXiv, Available online: https://arxiv.org/abs/2002.07526v1.
11. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development10.1109/JAS.2023.123618 ↗
12. Zakraoui, J., Saleh, M., Al-Maadeed, S., and Alja’am, J.M. (2020, January 7–9). Evaluation of Arabic to English Machine Translation Systems. Proceedings of the 2020 11th International Conference on Information and Communication Systems, ICICS 2020, Irbid, Jordan.10.1109/ICICS49469.2020.239518 ↗
13. The Key Challenges for Arabic Machine Translation10.1007/978-3-319-67056-0_8 ↗
14. Machine translation and the L2 classroom: Pedagogical solutions for making peace with Google translate10.1111/flan.12366 ↗
15. Satpathy, S., Mishra, S.P., and Nayak, A.K. (2019, January 25–26). Analysis of learning approaches for machine translation systems. Proceedings of the 2019 International Conference on Applied Machine Learning, ICAML 2019, Bhubaneswar, India.10.1109/ICAML48257.2019.00038 ↗
16. A ghostwriter in the machine? Attitudes of academic staff towards machine translation use in internationalised Higher Education10.1016/j.jeap.2021.100957 ↗
17. Rescigno, A.A., Monti, J., Way, A., and Vanmassenhove, E. (2020). A Case Study of Natural Gender Phenomena in Translation: A Comparison of Google Translate, Bing Microsoft Translator and DeepL for English to Italian, French and Spanish. Workshop on the Impact of Machine Translation (iMpacT 2020), Association for Machine Translation in the Americas (AMTA). Available online: https://aclanthology.org/2020.amta-impact.4.10.4000/books.aaccademia.8844 ↗
18. The impact of using machine translation on EFL students’ writing10.1080/09588221.2018.1553186 ↗
19. Survey on Evaluation Methods for Dialogue Systems10.1007/s10462-020-09866-x ↗
20. Integrating chatbots in education: Insights from the Chatbot-Human Interaction Satisfaction Model (CHISM)
21. Re-examining the chatBot Usability Scale (BUS-11) to assess user experience with customer relationship management chatbots10.1007/s00779-024-01834-4 ↗
22. Bodrunova, S.S. (2018). What Makes Users Trust a Chatbot for Customer Service? An Exploratory Interview Study. Internet Science, Springer International Publishing.10.1007/978-3-030-01437-7 ↗
23. A Survey of Evaluation Metrics Used for NLG Systems10.1145/3485766 ↗
24. Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002, January 6–12). Bleu: A Method for Automatic Evaluation of Machine Translation. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics—ACL ’02, Philadelphia, PA, USA.10.3115/1073083.1073135 ↗
25. Lin, C.-Y. (2025, June 18). ROUGE: A Package for Automatic Evaluation of Summaries. Available online: https://aclanthology.org/W04-1013/.
26. Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., and Artzi, Y. (2019). BERTScore: Evaluating Text Generation with BERT. arXiv, Available online: http://arxiv.org/abs/1904.09675.
27. Jurafsky, D., Chai, J., Schluter, N., and Tetreault, J. (2020, January 5–10). BLEURT: Learning Robust Metrics for Text Generation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.
28. Mehri, S., and Eskenazi, M. (2020, January 5–10). USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020), Online.10.18653/v1/2020.acl-main.64 ↗
29. Pillutla, K., Swayamdipta, S., Zellers, R., Thickstun, J., Choi, Y., and Harchaoui, Z. (2021). MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation. arXiv, Available online: https://arxiv.org/abs/2102.01454.
30. Burstein, J., Doran, C., and Solorio, T. (2019). Unifying Human and Statistical Evaluation for Natural Language Generation. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics.
31. Al-Harthi, M., and Al-Saif, A. (2019). The Design of the SauLTC application for the English-Arabic Learner Translation Corpus. Proceedings of the 3rd Workshop on Arabic Corpus Linguistics, Association for Computational Linguistics. Available online: https://aclanthology.org/W19-5610.
32. Designing AI-Powered Translation Education Tools: A Framework for Parallel Sentence Generation Using SauLTC and LLMs10.7717/peerj-cs.2788 ↗