A Methodological Review of Personalized and Conversational AI-Based Tutoring for Online Learning

Author

Ashtsiddhi Kadam, Vedika Wagh, Nikhil Walhe


Abstract

 While online learning platforms have democratized access to educational content, self-directed learners still face persistent challenges in structuring study materials, obtaining context-sensitive explanations, assessing comprehension, and monitoring mastery over time. Recent advancements in artificial intelligence address these limitations through personalized learning, intelligent tutoring systems (ITS), conversational agents, large language models (LLMs), retrieval-augmented generation (RAG), automated assessment, and learning analytics. This paper presents a methodology-focused review of 50 research studies charting the evolution of digital and self-directed learning toward personalized, conversational AI tutoring. We examine how learner profiles, adaptive mechanisms, conversational interaction, knowledge grounding, assessment routines, feedback generation, and learner-state tracking have been implemented and evaluated. Rather than classifying AI techniques in isolation, this review analyzes candidate methodologies based on their specific educational functions and architectural roles. Our synthesis indicates that while personalization, dialogue, grounding, assessment, and analytics are mature individual domains, their integration into an end-to-end, learner-centered tutoring loop remains limited. We formulate this gap as one of methodological fragmentation: curriculum grounding, contextual dialogue, learner-state modeling, assessment feedback, and longitudinal progress tracking are predominantly deployed as isolated modules. To resolve this fragmentation, we derive a set of methodological requirements for next-generation tutoring architectures—encompassing an LLM conversational layer, retrieval-based grounding, semantic content retrieval, a persistent learner model, adaptive assessment routines, targeted feedback, and cumulative progress tracking—establishing a traceable path from literature analysis to system design.


Keywords

personalized learning, intelligent tutoring systems, conversational AI, large language models, retrieval-augmented generation, learner modeling, adaptive assessment, learning analytics.



Full Text:

Download Paper PDF


References


The following 50 studies form the review reference set. Bibliographic fields were checked against available scholarly and publisher records; entries marked for verification require a final author/page check before submission.

[1] Choosing YouTube Videos for Self-Directed Learning, IEEE Access, 2022. DOI: 10.1109/ACCESS.2022.3174368.

[2] Learning Analytics of YouTube Videos Linked to LMS Moodle, MIPRO, 2021. DOI: 10.23919/MIPRO52101.2021.9597168.

[3] Relationship Between Cognitive Features and Social Media Engagement: An Analysis of YouTube Science Videos, IEEE Transactions on Engineering Management, 2023. DOI: 10.1109/TEM.2023.3330677.

[4] Exploring Digital Learning Pathways: Student Use of Online Information Resources and the Role of AI, WEEF-GEDC, 2024. DOI: 10.1109/WEEF-GEDC63419.2024.10854954.

[5] Investigating YouTube’s Educational Videos: Patterns, User Conduct and Suggestion Techniques, ICESIC, 2024. DOI: 10.1109/ICESIC61777.2024.10846554.

[6] AI-Based Learning Style Prediction in Online Learning for Primary Education, IEEE Access, 2022. DOI: 10.1109/ACCESS.2022.3160177.

[7] Personalized Learning Resource Recommendation Based On Learner Profile, IUCC/CIT/DSCI/SmartCNS, 2022. DOI: 10.1109/IUCC-CIT-DSCI-SmartCNS57392.2022.00040.

[8] A Framework of AI-based Intelligent Adaptive Tutoring System, ICCSE, 2021. DOI: 10.1109/ICCSE51940.2021.9569273.

[9] The Design and Development of an Adaptive Intelligent Tutoring System Based on Constructive Alignment and Cognitive Theories, JCSSE, 2022. DOI: 10.1109/JCSSE54890.2022.9836290.

[10] The Design of Guiding and Adaptive Prompts for Intelligent Tutoring Systems and Its Effect on Students’ Mathematics Learning, IEEE Transactions on Learning Technologies, 2024. DOI: 10.1109/TLT.2024.3382000.

[11] An Intelligent Serious Game for Digital Logic Education to Enhance Student Learning, IEEE, 2023.

[12] An Intelligent Tutoring System Proposal Based on Chatbot and Learning Styles to the Project Management Study, IEEE, 2023.

[13] Adaptive Versus Non-adaptive Mathematics Tutoring by Social Robots in Tanzanian Primary Schools, RO-MAN, 2025. DOI: 10.1109/RO-MAN63969.2025.11217562.

[14] Intelligent Adaptive Tutor with Career Recommendations, IGNITE, 2026. DOI: 10.1109/IGNITE69592.2026.11706244.

[15] Research on Intelligent Recommendation Algorithm of Online Learning Platform Based on Artificial Intelligence, EEBDA, 2024. DOI: 10.1109/EEBDA60612.2024.10485788.

[16] Generative AI for Personalized Learning and Education, ICISS, 2025. DOI: 10.1109/ICISS63372.2025.11076239.

[17] A Generative Artificial Intelligence Based Tutor for Personalized Learning, SmartBlock4Africa, 2024. DOI: 10.1109/SmartBlock4Africa61928.2024.10779525.

[18] Challenging the Confirmation Bias: Using ChatGPT as a Virtual Peer for Peer Instruction in Computer Programming Education, FIE, 2023. DOI: 10.1109/FIE58773.2023.10343247.

[19] Analyzing the Impact of AI-Driven Chatbots as Virtual English Tutors on English Language Learning and Engagement, ICAIQSA, 2024. DOI: 10.1109/ICAIQSA64000.2024.10882366.

[20] Personalization capabilities of current technology chatbots in a learning environment: An analysis of student-tutor bot interactions, Education and Information Technologies, 2025. DOI: 10.1007/s10639-025-13369-z.

[21] WIP: Beyond Code: Evaluating ChatGPT, Gemini, Claude, and Meta AI as AI Tutors in Computer Science and Engineering Education, FIE, 2024. DOI: 10.1109/FIE61694.2024.10893528.

[22] Exploring Students’ Perceptions of ChatGPT: Thematic Analysis and Follow-Up Survey, IEEE Access, 2023. DOI: 10.1109/ACCESS.2023.3268224.

[23] Learn Like Feynman: Developing and Testing an AI-Driven Feynman Bot, TALE, 2024. DOI: 10.1109/TALE62452.2024.10834370.

[24] Designing a Large Language Model Agent to Support Programming Problem Solving Based on Self-Regulated Learning, ICET, 2025. DOI: 10.1109/ICET67421.2025.11380763.

[25] AI Powered Academic Assistant Using Conversational AI, ICAECA, 2025. DOI: 10.1109/ICAECA63854.2025.11012528.

[26] Large Language Model in Higher Education: Leveraging Llama2 for Effective Academic Advising, ATC, 2024. DOI: 10.1109/ATC63255.2024.10908321.

[27] Exploration and Practice of Applying Large Language Models in Home Education Guidance, ICISE-IE, 2023. DOI: 10.1109/ICISE-IE60962.2023.10456439.

[28] OpenRAG: Open-source Retrieval-Augmented Generation Architecture for Personalized Learning, ICAIRC, 2024. DOI: 10.1109/ICAIRC64177.2024.10900069.

[29] An Interactive Question-Answering System Using Large Language Model and Retrieval-Augmented Generation in an Intelligent Tutoring System on the Programming Domain, ICAICTA, 2024. DOI: 10.1109/ICAICTA63815.2024.10763263.

[30] Intelligent Tutoring Agent with Retrieval-Augmented Generation: A Case Study of Quality Management System Course, ICCECE, 2025. DOI: 10.1109/ICCECE65250.2025.10984799.

[31] Accessible and Reliable AI Coding Tutors: Augmenting Large Language Models with Retrieval-Augmented Generation for Java Programming, EDUCON, 2025. DOI: 10.1109/EDUCON62633.2025.11016497.

[32] Combining RAG, LLMs, Vector Databases and Semantic Search in Intelligent Tutoring Systems, ICSCSS, 2026. DOI: 10.1109/ICSCSS69635.2026.11645972.

[33] Retrieval-Augmented Generation for Scalable, Context-Aware Educational Tools, NKCon, 2025. DOI: 10.1109/NKCon66957.2025.11345779.

[34] Aduvia: A Multi-Purpose AI-Powered Learning Management System (LMS), NILES, 2025. DOI: 10.1109/NILES68063.2025.11231978.

[35] Design and Implementation of a Personalized AI Tutor for University Education Using RAG, Redžúr, 2025. [Bibliographic metadata verification required.]

[36] From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle, arXiv, 2026. [Bibliographic metadata verification required.]

[37] Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education, ACL BEA, 2026. DOI: 10.18653/v1/2026.bea-1.57.

[38] MCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning, IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3420709.

[39] Enhancing Engineering Education Through LLM-Driven Adaptive Quiz Generation: A RAG-Based Approach, FIE, 2024. DOI: 10.1109/FIE61694.2024.10893146.

[40] Quiz Generation and Chat Interaction with LLMs: A Design and Implementation of an AI-Based LMS, SoftCOM, 2025. DOI: 10.23919/SoftCOM66362.2025.11197405.

[41] Research on Automatic Question Generation Methods for Niche Subjects Based on Large Language Models, ICEIT, 2025. DOI: 10.1109/ICEIT64364.2025.10976111.

[42] Real-Time Question Generation from Educational Video Lectures using Deep Learning, WCONF, 2025. DOI: 10.1109/WCONF64849.2025.11233372.

[43] Comparative Analysis of Large Language Models for Automated Question Generation From Video-Based Learning Content, IEEE Transactions on Artificial Intelligence, 2025. DOI: 10.1109/TAI.2025.3620274.

[44] Automatic Question Generation for Cognitive Domain of Outcome-Based Education System, ICIT, 2024. DOI: 10.1109/ICIT63607.2024.10860228.

[45] A Three-Stage Framework for Large Language Model–Assisted Formative Assessment and Actionable Feedback in Teacher Education, ICAITE, 2025. DOI: 10.1109/ICAITE68636.2025.11442463.

[46] Personalized Assessment in Education: Enhancing MCQ Generation Using Advanced AI and Contextual Learning Models, CCUBE, 2025. DOI: 10.1109/CCUBE66458.2025.11340281.

[47] EvalIA: Towards a Hybrid AI-Supported Platform for Oral Performance Assessment, EDUCON, 2026. DOI: 10.1109/EDUCON67543.2026.11574279.

[48] Large Language Model-Based Multimodal Learning Analytics and Intelligent Path Planning, ICISE-IE, 2025. DOI: 10.1109/ICISE-IE68873.2025.11379719.

[49] Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AI, IEEE publication record, 2025. [Bibliographic metadata verification required.]

[50] Exploring the Efficacy of ChatGPT in an Undergraduate Electronics Course through Comparative Analysis of Circuit Problem Solving, iSTEM-Ed, 2025. DOI: 10.1109/iSTEM-Ed65612.2025.11129294.

Share your valuable work from Social Media Buttons