Science AI Journal
Computer Science · Research topic

Open research questions in Intelligent Tutoring Systems and Adaptive Learning

496 gap statements mined from Intelligent Tutoring Systems and Adaptive Learning papers in our 7.9M-paper local library, which holds 2,955 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.

Choosing where to publish on Intelligent Tutoring Systems and Adaptive Learning? See the ranked Computer Science journals.

What the literature leaves open

  • The study highlights the need for a more accurate method for deriving review intervals from these estimates. The paper notes that current methods for estimating time-related decline may be biased by rapid repetitions.

    Estimating time-related decline from mathematics platform logs: rapid repetition, learner variation, and model-implied review intervals · 2026 · DOI

  • The need for improved scheduling assistance in education. The potential of applying Reinforcement Learning for personalized exam scheduling. The lack of effective algorithms for handling complex student learning trajectories.

    AI-Based Intelligent System for Personalized Examination Scheduling · 2025 · DOI

  • There is a need to explore how AI tools like ChatGPT can support personalized learning experiences. There is a lack of understanding of how ChatGPT can facilitate self-regulated learning processes and learning computer programming.

    Artificial Intelligence Supporting Independent Student Learning: An Evaluative Case Study of ChatGPT and Learning to Code · 2024 · DOI

  • The need for technology to support teachers with tasks such as assessment and feedback. The gap in using artificial intelligence to support peer-to-peer discussions in science classrooms.

    Using Artificial Intelligence to Support Peer-to-Peer Discussions in Science Classrooms · 2024 · DOI

  • Lack of interpretability and trustworthiness in artificial intelligence methods for educational challenges. Difficulty in integrating existing educational causal relationships into sub-symbolic methods. Need for approaches that can process temporal dynamics and relationships in data for early predictive modeling tasks.

    Memory-Based Dynamic Bayesian Networks for Learner Modeling: Towards Early Prediction of Learners’ Performance in Computational Thinking · 2024 · DOI

  • On-policy distillation (OPD) is increasingly used for language model post-training, yet how teacher supervision shapes learning and forgetting remains unclear.

    OPDArena: Understanding Learning and Forgetting in On-Policy Distillation · 2026

  • Cognitive disengagement during intelligent tutoring system (ITS) interactions has been extensively characterized in terms of state detection and prevalence, yet the behavioral dynamics governing recovery from negative episodes remain poorly understood.

    From disengagement to re-engagement: behavioral evidence for AI-driven adaptive tutoring interventions in intelligent tutoring systems · 2026 · DOI

  • Future work will focus on few-shot learner modeling to mitigate data sparsity, the incorporation of lightweight adapter modules to improve scalability, and the extension of TAS-AF to multilingual and cross-domain writing tasks to broaden its applicability in diverse educational contexts.

    CNN–transformer-based trait-aware scoring and student-aware feedback generation for English writing · 2026 · DOI

  • Many challenges remain in the systematic and sustainable integration of prompt engineering in education. Most available research relies on short-term interventions, cross-sectional designs, and self-reported measures of attitudes and perceptions.

    Prompt engineering in education: A systematic review of theory, applications, and future directions · 2026 · DOI

  • The lack of explainability in AI-driven assessment systems. The absence of meaningful feedback in traditional assessment systems.

    An Explainable AI-Driven Intelligent Assessment and Learning Analytics Platform · 2026 · DOI

  • Cognitive biases and lack of experience can hinder diagnostic reasoning. SBL environments require effective scaffolding to support learning. The use of large language models and learning analytics is a relatively new area of research.

    Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning · 2026 · DOI

  • The study had a relatively small sample size (n = 63). The study only examined two scaffolding approaches, and further research is needed to explore other approaches. The study used a simulated environment, and further research is needed to explore the effectiveness of the approach in real-world settings.

    Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning · 2026 · DOI

  • The need to integrate domain-specific scientific representations with domain-general computational concepts. The challenge of capturing the processes and behaviors that shape student learning in complex STEM+C settings.

    Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning · 2026 · DOI

  • The gap in the literature is the lack of research on detecting socially shared regulation behaviors in collaborative STEM+C learning environments. Prior work has focused on individualized problem-solving instead of collaborative, open-ended problem-solving.

    Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning · 2026 · DOI

  • The lack of an integrated platform that combines skill assessment, resume optimization, and AI-driven interview simulation.

    An AI-Driven Multimodal Framework for Interview Readiness Assessment and Skill Enhancement · 2026 · DOI

  • Conventional preparation strategies often fail to provide personalized guidance and adaptive feedback. There is a need for an AI-powered study assistant that can address the challenges faced by GATE aspirants.

    AI Powered Study Assistant for GATE Aspirants: Personalized, Adaptive, Smart Learning Planner · 2026 · DOI

  • Students faced difficulties in building collaborative relationships with Gen AI, particularly when asking Gen AI to explain its code or provide solutions to errors. Students struggled with understanding Gen AI's answers and felt that they lacked basic programming knowledge. Students relied heavily on Gen AI when interacting with it, which hindered their ability to develop self-regulated learning skills.

    Benefits and Challenges of Collaboration between Students and Conversational Generative Artificial Intelligence in Programming Learning: An Empirical Case Study · 2024 · DOI

  • Based on the findings of this literature review, several recommendations can be proposed for educators, researchers, and policymakers. First, educational institutions should encourage the systematic integration of AI-supported tools into science curricula.

    Artificial Intelligence-supported applications used in Science Education · 2026 · DOI

  • The difficulty of scaling high-quality instructional support through human provision alone - The challenge of structuring learners' reasoning processes - The need to develop mechanisms that condition scaffold generation on explicit task…

    Artificial intelligence as the More Knowledgeable Other (MKO) 2.0: metadata-driven adaptive scaffolding for narrative comprehension · 2026 · DOI

  • Investigating the use of explicit task characteristics to condition scaffold generation. Examining the effectiveness of MKO 2.0 in different educational contexts. Developing mechanisms to structure or steer LLM generation toward specified instructional strategies.

    Artificial intelligence as the More Knowledgeable Other (MKO) 2.0: metadata-driven adaptive scaffolding for narrative comprehension · 2026 · DOI

  • Investigating the application of other RL algorithms for personalized exam scheduling, - Exploring the use of AI-based instructional support systems in other educational settings, - Developing more comprehensive datasets to evaluate the performance of RL…

    AI-Based Intelligent System for Personalized Examination Scheduling · 2025 · DOI

  • Further research could explore the application of this agent in various educational settings - The development of more advanced MDP frameworks could lead to improved performance - Investigating the use of other large language models and their impact on the agent's…

    CPU-Only Self Enhancing Authoring Copilot Design-Based Markov Decision Processes Orchestration and Qwen 3 Local Large Language Model · 2025 · DOI

  • Investigating the effectiveness of ChatGPT in supporting learning in different subjects and contexts, - Examining the impact of ChatGPT on learners' metacognitive skills, - Exploring the potential of ChatGPT to provide personalized learning experiences, - Studying the limitations of ChatGPT and how to address…

    Artificial Intelligence Supporting Independent Student Learning: An Evaluative Case Study of ChatGPT and Learning to Code · 2024 · DOI

  • The study only used data from two classrooms at the same school, - The study had a limited sample size of 256 students, - The study did not compare the chat tool to other methods of facilitating peer…

    Using Artificial Intelligence to Support Peer-to-Peer Discussions in Science Classrooms · 2024 · DOI

  • Expanding the dataset to include diverse educational games or scenarios - Extending the temporal scope or implementing dynamic sequence lengths - Deploying the proposed model in other real-world educational…

    Memory-Based Dynamic Bayesian Networks for Learner Modeling: Towards Early Prediction of Learners’ Performance in Computational Thinking · 2024 · DOI

Most-cited papers in Intelligent Tutoring Systems and Adaptive Learning

Most recent work

Find a gap in your own Intelligent Tutoring Systems and Adaptive Learning sub-topic

This page shows what the Intelligent Tutoring Systems and Adaptive Learning literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 7.9M-paper local library and writes the gaps from its rows.

Open the Research Gap Finder →

Related topics in Computer Science

Online Learning and Analytics
1,253 open questions
Advanced Neural Network Applications
1,236 open questions
AI in Service Interactions
1,161 open questions
Virtual Reality Applications and Impacts
1,060 open questions
Computational Drug Discovery Methods
1,019 open questions
Quantum Computing Algorithms and Architecture
877 open questions
AI in cancer detection
835 open questions
Topic Modeling
780 open questions
Open questions raised by papers listed on this page include: (1) Cognitive biases and lack of experience can hinder diagnostic reasoning (“Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in…”, 2026); (2) The gap in the literature is the lack of research on detecting socially shared regulation behaviors in collaborative STEM+C learning environments (“Using Large Language Models to Detect Socially Shared Regulation of…”, 2026); (3) The lack of an integrated platform that combines skill assessment, resume optimization, and AI-driven interview simulation (“An AI-Driven Multimodal Framework for Interview Readiness Assessment and Skill…”, 2026); (4) There is a need for an AI-powered study assistant that can address the challenges faced by GATE aspirants (“AI Powered Study Assistant for GATE Aspirants: Personalized, Adaptive, Smart…”, 2026); (5) On-policy distillation (OPD) is increasingly used for language model post-training, yet how teacher supervision shapes learning and forgetting remains unclear (“OPDArena: Understanding Learning and Forgetting in On-Policy Distillation”, 2026). 496 gap statements have been mined from Intelligent Tutoring Systems and Adaptive Learning papers in our 7.9M-paper local library, which holds 2,955 papers on the topic; the gaps come from whichever of those papers state one. They are mostly the research gaps the authors state and the papers' abstracts, plus future-work, limitations and challenges passages. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 1,100,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? Acceptance odds for top, mid and open/emerging journals, in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck for prior publication across 7 sources and our local library.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

How Pre-Check worksHow AI Review works

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.