International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 18, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 1996KB)
EduAgent: A Multimodal Chatbot Framework for Enhancing Interactive Learning in Electrical and Electronics Engineering Education
PDF (1996KB), PP.104-125
Views: 0 Downloads: 0
Author(s)
Sayem Shahad
1,*
Salman Sayeed
1
Md Naimur Rahman Khan Sifat
2
Shuvo Biswas
2
Tishna Sabrina
2
Index Terms
LLM, Chat Agent, Retriever, Pedagogical Response, Prompt Engineering, Fine Tuning
Abstract
In recent days, we have largely adopted Advanced Large Language Models (LLMs) in educational settings, where we use them as content creators, teaching assistants, and interactive conversation agents. However, the responses generated by these models are often monotonous, verbose, and ambiguous, which can hinder their effectiveness in educational contexts. Addressing these shortcomings, we introduce EduAgent, a multimodal chatbot framework specifically designed to enhance interactive learning in Electrical and Electronics Engineering (EEE) education. EduAgent can respond with pedagogically enhanced answers to electronics-related queries, complemented by relevant images and detailed explanations. It is designed to provide complete, concise, step-by-step responses, ensuring that foundational knowledge is clearly mentioned before diving deep. To develop EduAgent, we constructed a dataset comprising 596 four-turn conversations and a collection of 118 images covering a wide range of EEE concepts. The conversation dataset was used to fine-tune the open-source LLMs and facilitate in-context learning. Both images and their corresponding explanations were integrated into a knowledge base for efficient retrieval. Finally, we evaluated multiple text generation and image retrieval methods using both automatic metrics and human assessments, demonstrating the effectiveness and engagement of our approach.
Cite This Paper
Sayem Shahad, Salman Sayeed, Md Naimur Rahman Khan Sifat, Shuvo Biswas, Tishna Sabrina, "EduAgent: A Multimodal Chatbot Framework for Enhancing Interactive Learning in Electrical and Electronics Engineering Education", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.1, pp. 104-125, 2026. DOI:10.5815/ijmecs.2026.01.07
Reference
[1]Lijia Chen, Pingping Chen, and Zhijian Lin. “Artificial Intelligence in Education: A Review”. In: IEEE Access 8 (2020), pp. 75264–75278. DOI: 10.1109/ACCESS.2020.2988510.
[2]Josh Achiam et al. “Gpt-4 technical report”. In: arXiv preprint arXiv:2303.08774 (2023).
[3]Gemini Team et al. Gemini: A Family of Highly Capable Multimodal Models. 2024. arXiv: 2312.11805 [cs.CL].URL: https://arxiv.org/abs/2312.11805.
[4]Jacob Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 2019. arXiv: 1810.04805 [cs.CL]. URL: https://arxiv.org/abs/1810.04805.
[5]David Duran. “Learning-by-teaching. Evidence and implications as a pedagogical mechanism”. In: Innovations in education and teaching international 54.5 (2017), pp. 476–484.
[6]Pamela M Ironside. “Using narrative pedagogy: learning and practising interpretive thinking”. In: Journal of ad- vanced nursing 55.4 (2006), pp. 478–486.
[7]Aarika Pardino et al. “The best pedagogical practices in graduate online learning: A systematic review”. In: Creative Education 9.07 (2018), p. 1123.
[8]Bashaer Alsafari et al. “Towards effective teaching assistants: From intent-based chatbots to LLM-powered teach- ing assistants”. In: Natural Language Processing Journal 8 (2024), p. 100101.
[9]Mahyar Abbasian et al. “Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Dia- betes Patients”. In: arXiv preprint arXiv:2402.10153 (2024).
[10]Zheyuan Zhang et al. Simulating Classroom Education with LLM-Empowered Agents. 2024. arXiv: 2406.19226 [cs.CL]. URL: https://arxiv.org/abs/2406.19226.
[11]Robin Schmucker et al. “Ruffle&riley: Towards the automated induction of conversational tutoring systems”. In:arXiv preprint arXiv:2310.01420 (2023).
[12]AN Sixu et al. “Developing an LLM-Empowered Agent to Enhance Student Collaborative Learning Through Group Discussion”. In: International Conference on Computers in Education. 2024.
[13]Nasrin Dehbozorgi, Mourya Teja Kunuku, and Seyedamin Pouriyeh. “Personalized Pedagogy Through a LLM- Based Recommender System”. In: International Conference on Artificial Intelligence in Education. Springer. 2024, pp. 63–70.
[14]Cecilia Ka Yuk Chan and Louisa HY Tsi. “The AI revolution in education: Will AI replace or assist teachers in higher education?” In: arXiv preprint arXiv:2305.01185 (2023).
[15]Barak Rosenshine. “Principles of instruction: Research-based strategies that all teachers should know.” In: Ameri- can educator 36.1 (2012), p. 12.
[16]Jacob Devlin. “Bert: Pre-training of deep bidirectional transformers for language understanding”. In: arXiv preprint arXiv:1810.04805 (2018).
[17]Tom Brown et al. “Language models are few-shot learners”. In: Advances in neural information processing systems 33 (2020), pp. 1877–1901.
[18]James Finnie-Ansley et al. “The robots are coming: Exploring the implications of openai codex on introductory programming”. In: Proceedings of the 24th Australasian Computing Education Conference. 2022, pp. 10–19.
[19]Aakanksha Chowdhery et al. “Palm: Scaling language modeling with pathways”. In: Journal of Machine Learning Research 24.240 (2023), pp. 1–113.
[20]Jordan Hoffmann et al. “Training compute-optimal large language models”. In: arXiv preprint arXiv:2203.15556(2022).
[21]Hugo Touvron et al. “Llama: Open and efficient foundation language models”. In: arXiv preprint arXiv:2302.13971(2023).
[22]Albert Q Jiang et al. “Mistral 7B”. In: arXiv preprint arXiv:2310.06825 (2023).
[23]Marah Abdin et al. “Phi-3 technical report: A highly capable language model locally on your phone”. In: arXiv preprint arXiv:2404.14219 (2024).
[24]H. Dang et al. “How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models”. In: CHI’22 Workshops, New Orleans, LA. 2022.
[25]D. Alivanistos et al. Prompting as Probing: Using Language Models for Knowledge Base Construction. 2022. URL:https://github.com/HEmile/iswc-challenge.
[26]S. Arora et al. ASK ME ANYTHING: A SIMPLE STRATEGY FOR PROMPTING LANGUAGE MODELS. 2023. URL: https://github.com/HazyResearch/ama_prompting.
[27]B. Chen et al. “Unleashing the potential of prompt engineering in Large Language Models: a comprehensive re- view”. In: (2024). eprint: arXiv:2310.14735.
[28]Xuezhi Wang et al. “Self-consistency improves chain of thought reasoning in language models”. In: arXiv preprint arXiv:2203.11171 (2022).
[29]Stephen Robertson, Hugo Zaragoza, et al. “The probabilistic relevance framework: BM25 and beyond”. In: Foundations and Trends® in Information Retrieval 3.4 (2009), pp. 333–389.
[30]Edward J Hu et al. “Lora: Low-rank adaptation of large language models”. In: arXiv preprint arXiv:2106.09685(2021).
[31]L. Dai et al. “A systematic review of pedagogical agent research: Similarities, differences and unexplored aspects”. In: Computers & Education 190 (2022), p. 104607. DOI: 10.1016/j.compedu.2022.104607.
[32]P. Sikstro¨m et al. “How pedagogical agents communicate with students: A two-phase systematic review”. In: Com- puters & Education 188 (2022), p. 104564. DOI: 10.1016/j.compedu.2022.104564.
[33]F. Weber et al. Pedagogical Agents for Interactive Learning: A Taxonomy of Conversational Agents in Education. Completed Research Paper. 2022.
[34]J. C. Castro-Alonso et al. “Effectiveness of Multimedia Pedagogical Agents Predicted by Diverse Theories: a Meta-Analysis”. In: Educational Psychology Review 33 (2021), pp. 989–1015. DOI: 10.1007/s10648-020- 09629-1.
[35]R. O. Davis, T. Park, and J. Vincent. “A Meta-Analytic Review on Embodied Pedagogical Agent Design and Testing Formats”. In: Journal of Educational Computing Research 61.1 (2023), pp. 30–67. DOI: 10 . 1177 / 07356331221100556.
[36]R. Schlimbach et al. “A Literature Review on Pedagogical Conversational Agent Adaptation”. In: Pacific Asia Conference on Information Systems 2022. 2022.
[37]Zongxi Li et al. “Retrieval-augmented generation for educational application: A systematic survey”. In: Computers and Education: Artificial Intelligence (2025), p. 100417.
[38]Umair Hasan Khan, Muneeb Hasan Khan, and Rashid Ali. “Large Language Model based Educational Virtual Assistant using RAG Framework”. In: Procedia Computer Science 252 (2025), pp. 905–911.
[39]Chengshuai Zhao et al. “CyberBOT: Towards Reliable Cybersecurity Education via Ontology-Grounded Retrieval Augmented Generation”. In: arXiv preprint arXiv:2504.00389 (2025).
[40]Andreas Martin et al. “ChEdBot: designing a domain-specific conversational agent in a simulational learning envi- ronment using LLMs”. In: Proceedings of the AAAI Symposium Series. Vol. 3. 1. 2024, pp. 180–187.
[41]Horia Alexandru Modran et al. “LLM intelligent agent tutoring in higher education courses using a RAG approach”. In: International Conference on Interactive Collaborative Learning. Springer. 2024, pp. 589–599.
[42]N Reddy. “Design and Implementation of an AI-Based Chatbot Framework with Retrieval-Augmented Generation and Integrated Recommender System for Interactive User Support”. In: Available at SSRN 5250507 (2025).
[43]Karan Singhal et al. “Towards expert-level medical question answering with large language models”. In: arXiv preprint arXiv:2305.09617 (2023).
[44]Renqian Luo et al. “BioGPT: generative pre-trained transformer for biomedical text generation and mining”. In:Briefings in bioinformatics 23.6 (2022), bbac409.
[45]A. J. Thirunavukarasu et al. “Large language models in medicine”. In: Nature Medicine 29.9 (2023), pp. 1740–1747. DOI: 10.1038/s41591-023-02448-8.
[46]M. Wornow et al. “The shaky foundations of large language models and foundation models for electronic health records”. In: npj Digital Medicine 6 (2023), p. 135. DOI: 10.1038/s41746-023-00725-2.
[47]X. Yang et al. “A large language model for electronic health records”. In: npj Digital Medicine 5 (2022), p. 194. DOI: 10.1038/s41746-022-00654-y.
[48]J. G. Meyer et al. “ChatGPT and large language models in academia: opportunities and challenges”. In: BioData Mining 16 (2023), p. 20. DOI: 10.1186/s13040-023-00270-9.
[49]E. Kasneci et al. “ChatGPT for good? On opportunities and challenges of large language models for education”. In: Learning and Individual Differences (2023), p. 102274. DOI: 10.1016/j.lindif.2023.102274.
[50]F. F. Xu et al. “A systematic evaluation of large language models of code”. In: MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming. 2022, pp. 1–10. DOI: 10.1145/3520312. 3534862.
[51]J. Huang et al. “Current state of large language models: Opportunities and challenges in artificial intelligence”. In:Artificial Intelligence Review 56.2 (2023), pp. 1377–1400. DOI: 10.1007/s10462-022-10207-0.
[52]A. Maatouk et al. “Large language models for telecom: forthcoming impact on the industry”. In: IEEE Communi- cations Magazine (2024). Early Access, pp. 1–7. DOI: 10.1109/MCOM.001.2300473.
[53]K. S. Unnithan. “An empirical study on Natural Language Processing in identifying industry demands to recom- mends required qualifications in the UAE”. Dissertation submitted in fulfillment of the requirement for the degree of MSc Informatics (Knowledge & Data Management). MA thesis. The British University in Dubai, 2021.
[54]M. U. Hadi et al. A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage. Computing and Processing, General Topics for Engineers. 2023. DOI: 10.1007/sXXXX-XXXX-XX.
[55]R. Ruffle and J. Riley. “The Future of Large Language Models: Opportunities and Ethical Considerations”. In:Journal of Artificial Intelligence Research 75 (2024), pp. 1–15. DOI: 10.1007/sXXXX-XXXX-XX.
[56]C. Zhou et al. “A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT”. In: (2023). arXiv preprint. DOI: 10.48550/arXiv.2302.09419.
[57]Z. Kong et al. “Entity Extraction of Electrical Equipment Malfunction Text by a Hybrid Natural Language Process- ing Algorithm”. In: IEEE Access 9 (2021), pp. 40954–40963. DOI: 10.1109/ACCESS.2021.3063354.
[58]Thanh Nguyen Ngoc et al. AI-assisted Learning for Electronic Engineering Courses in High Education. 2023. arXiv: 2311.01048 [cs.CY]. URL: https://arxiv.org/abs/2311.01048.
[59]Ishika Joshi et al. ”With Great Power Comes Great Responsibility!”: Student and Instructor Perspectives on the in- fluence of LLMs on Undergraduate Engineering Education. 2023. arXiv: 2309.10694 [cs.HC]. URL: https://arxiv.org/abs/2309.10694.
[60]Pragati Shuddhodhan Meshram et al. ElectroVizQA: How well do Multi-modal LLMs perform in Electronics Visual Question Answering? 2024. arXiv: 2412.00102 [cs.CV]. URL: https://arxiv.org/abs/2412. 00102.
[61]Xiaoyi Dong et al. InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model. 2024. arXiv: 2401.16420 [cs.CV]. URL: https://arxiv.org/abs/ 2401.16420.
[62]Llama3.1-8b-Instruct Unsloth model. URL: https://huggingface.co/unsloth/Meta-Llama-3.1- 8B-Instruct-bnb-4bit.
[63]Llama3.2-3b-Instruct Unsloth model. URL: https://huggingface.co/unsloth/Llama- 3.2- 3B- Instruct.
[64]Unsloth GitHub repository. URL: https://github.com/unslothai/unsloth.
[65]Jiawei Shao, Yuyi Mao, and Jun Zhang. Task-Oriented Communication for Multi-Device Cooperative Edge Infer- ence. 2023. arXiv: 2109.00172 [eess.SP]. URL: https://arxiv.org/abs/2109.00172.
[66]Kishore Papineni et al. “Bleu: a Method for Automatic Evaluation of Machine Translation”. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Ed. by Pierre Isabelle, Eugene Charniak, and Dekang Lin. Philadelphia, Pennsylvania, USA: Association for Computational Linguistics, July 2002, pp.311-318. DOI:10.3115/1073083.1073135. URL: https://aclanthology.org/P02-1040/.
[67]Sacrebleu. URL: https://github.com/mjpost/sacrebleu.
[68]Gerard Salton, Anita Wong, and Chung-Shu Yang. “A vector space model for automatic indexing”. In: Communi- cations of the ACM 18.11 (1975), pp. 613–620.