pith. machine review for the scientific record. sign in

arxiv: 2605.06257 · v1 · submitted 2026-05-07 · 💻 cs.HC

Recognition: unknown

LearnMate²: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning

Xinyu Jessica Wang , Christine P. Lee , Bilge Mutlu
Authors on Pith no claims yet

Pith reviewed 2026-05-08 07:11 UTC · model grok-4.3

classification 💻 cs.HC
keywords online learningpersonalized learningadaptive systemsLLM applicationsuser experienceAI in educationlearning outcomes
0
0 comments X

The pith

An LLM system for online courses creates custom study plans and real-time help that raise learning gains and user satisfaction.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents LearnMate^2, a tool built around large language models to deliver personalized study plans, immediate contextual assistance during tasks, and activities that adjust to the learner's progress. Two user studies, one with 24 participants to refine the design and one with 16 to compare against standard platforms plus separate LLM support, found better learning results and smoother experiences with the integrated system. A sympathetic reader would care because most open online courses offer little guidance, leading to high dropout; this approach aims to supply scalable, on-demand personalization without constant human involvement. If the gains hold, online education could shift from uniform content delivery to adaptive support that tracks individual needs in real time.

Core claim

LearnMate^2 advances AI pedagogy by improving both learning outcomes and user experience compared to existing online learning and support tools. It does so by iteratively designing features that combine personalized study plans, real-time contextual assistance, and adaptive learning activities powered by large language models, with evaluations showing advantages over combinations of established platforms and standalone LLM support.

What carries the argument

LearnMate^2, the integrated LLM-powered system that generates personalized study plans, supplies real-time contextual assistance, and adapts activities based on user progress.

Load-bearing premise

The results from small groups doing short, specific tasks will apply to larger, varied populations using the system over longer periods in actual courses.

What would settle it

A follow-up study with hundreds of diverse students across multiple courses and several weeks of use showing no improvement or lower outcomes and satisfaction for LearnMate^2 compared to control groups.

Figures

Figures reproduced from arXiv: 2605.06257 by Bilge Mutlu, Christine P. Lee, Xinyu Jessica Wang.

Figure 1
Figure 1. Figure 1: From fixed online learning workflows to personalized and adaptive support — The figure contrasts a typical online learning workflow (left), where learners often struggle with cold start problems ( A ), limited timely support ( B ), and fixed learning plans ( C ), with the LearnMate2 workflow (right). LearnMate2 addresses these challenges through PlanMate for person￾alized study planning ( A ), StudyMate fo… view at source ↗
Figure 2
Figure 2. Figure 2: LearnMate2 System Workflow — The front-end interface of LearnMate2 (left) and the system workflow (right). The three-step integrated learning loop shows how PlanMate, StudyMate, and AdaptMate work together to provide personalized study planning, real-time contextual assistance, and adaptive learning activities that adjust based on user progress and performance. We outline and explain the pipeline of LearnM… view at source ↗
Figure 3
Figure 3. Figure 3: PlanMate Interface — The front-end interface for personalized study planning. Users begin by specifying their learning goals in natural language (step a ), then provide preferences across multiple dimensions, including time availability, learning pace, and content path (steps b to c ). Based on these inputs, PlanMate generates a personalized study plan in text form (step d ) and visualizes it as an interac… view at source ↗
Figure 4
Figure 4. Figure 4: StudyMate Interface — The front-end interface for interactive learning support during scheduled study sessions. Users start a learning session by selecting a planned time slot (step f ), after which StudyMate provides session-specific guidance. During the session, users can ask questions and receive contextual assistance with progressive disclosure options, including more details, practice questions, and e… view at source ↗
Figure 5
Figure 5. Figure 5: AdaptMate Interface — The front-end interface for adaptive plan refinement based on learning performance. After completing a study session and quiz, users receive a detailed performance report with learning insights (step l ). Users can then request plan adjustments (step m), and AdaptMate generates an updated study plan that incorporates quiz results, interaction patterns, and prior preferences, presented… view at source ↗
Figure 6
Figure 6. Figure 6: Quantitative Data from User Study— Bar graphs show participants’ quiz results for Quiz 1 and Quiz 2. Hori￾zontal lines indicate significant pairwise comparisons with paired t-tests (𝑝 < .05∗ , 𝑝 < .01∗∗ , 𝑝 < .001∗∗∗). Vertical lines in each bar graph indicate standard error. generation, real-time contextual assistance during learning, and adaptive learning activities that adjust based on ongoing progress … view at source ↗
Figure 7
Figure 7. Figure 7: Quantitative Data from User Study — Bar graphs on participants’ perceived performance of usefulness, ease of use, ease of learning, satisfaction and usability scores across different conditions for the planning task (T1). Horizontal lines indicate significant pairwise comparisons with repeated measures ANOVA (𝑝 < .05∗ , 𝑝 < .01∗∗ , 𝑝 < .001∗∗∗). Vertical lines in each bar graph indicate standard error. qua… view at source ↗
Figure 8
Figure 8. Figure 8: Quantitative Data from User Study— Bar graphs on participants’ perceived performance of usefulness, ease of use, ease of learning, satisfaction and usability scores across different conditions for the studying task (T2). Horizontal lines indicate significant pairwise comparisons with repeated measures ANOVA (𝑝 < .05∗ , 𝑝 < .01∗∗ , 𝑝 < .001∗∗∗). Vertical lines in each bar graph indicate standard error view at source ↗
Figure 9
Figure 9. Figure 9: Quantitative Data from User Study— Bar graphs on participants’ perceived performance of usefulness, ease of use, ease of learning, satisfaction and usability scores across different conditions for the adapting task (T3). Horizontal lines indicate significant pairwise comparisons with repeated measures ANOVA (𝑝 < .05∗ , 𝑝 < .01∗∗ , 𝑝 < .001∗∗∗). Vertical lines in each bar graph indicate standard error. but … view at source ↗
read the original abstract

Personalization is crucial for effective learning, yet online learning, designed for widespread availability and open access, lacks personalized guidance. Recent advancements in large language models (LLMs) offer opportunities to bridge this gap. We explore how LLM-driven tools may be designed to support personalized and adaptive learning and examine how they shape user experience and learning outcomes. We iteratively designed \tool{} to support online learning by providing personalized study plans, real-time contextual assistance, and adaptive learning activities. A preliminary study ($n=24$) assessed the effectiveness and usability of \tool{} and informed refinements in our system, which we then evaluated ($n = 16$) against a combination of a state-of-the-art online learning platform and an LLM for learning support. Results indicate that \tool{} advances AI pedagogy by improving both learning outcomes and user experience compared to existing online learning and support tools. This work advances our understanding of the design space of personalized, AI-driven educational tools and their potential impact on user experience.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript presents LearnMate^2, an LLM-powered system for online learning that provides personalized study plans, real-time contextual assistance, and adaptive activities. It describes an iterative design process informed by a preliminary usability study (n=24) and reports results from a subsequent comparative evaluation (n=16) against a state-of-the-art online learning platform combined with a separate LLM support tool, claiming superior learning outcomes and user experience.

Significance. If substantiated, the work would contribute to AI-enhanced education by showing the value of an integrated LLM approach for personalization over modular baselines. The iterative, user-centered design process is a clear strength, as is the attempt to evaluate both performance metrics and experiential outcomes in a comparative setting. The paper advances understanding of the design space for such tools.

major comments (2)
  1. [Comparative Evaluation] The headline claim of improved learning outcomes rests on the n=16 comparative study. The manuscript provides no details on the specific outcome measures (e.g., pre/post-test scores, task completion accuracy), statistical tests performed, p-values, effect sizes, or power analysis. Without these, the reported positive results cannot be assessed for reliability given the small sample and known noise in learning-gain data.
  2. [Comparative Evaluation] No information is given on controls for individual variance, prior knowledge, or task selection to mitigate ceiling effects. The baseline condition (state-of-the-art platform + LLM) is also underspecified, preventing clear attribution of any gains to the integrated design of LearnMate^2 rather than implementation differences.
minor comments (1)
  1. [Abstract] The abstract would be more informative if it briefly noted the sample sizes and the direction of the observed improvements.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback, which identifies key areas where additional detail will improve the transparency and interpretability of our comparative evaluation. We address each comment below and will revise the manuscript to incorporate the requested information and clarifications.

read point-by-point responses

  1. Referee: The headline claim of improved learning outcomes rests on the n=16 comparative study. The manuscript provides no details on the specific outcome measures (e.g., pre/post-test scores, task completion accuracy), statistical tests performed, p-values, effect sizes, or power analysis. Without these, the reported positive results cannot be assessed for reliability given the small sample and known noise in learning-gain data.

    Authors: We agree that the current manuscript omits critical statistical details necessary for assessing result reliability. In the revised version, we will expand the evaluation section to explicitly describe the outcome measures (pre/post-test scores on standardized quizzes covering core concepts plus task completion accuracy), the statistical tests applied (independent t-tests with Welch correction for between-group comparisons and paired tests for within-group gains), exact p-values, effect sizes (Cohen's d), and a dedicated limitations paragraph addressing the small sample size, absence of a priori power analysis, and implications for generalizability. These additions will enable readers to evaluate the findings appropriately. revision: yes

  2. Referee: No information is given on controls for individual variance, prior knowledge, or task selection to mitigate ceiling effects. The baseline condition (state-of-the-art platform + LLM) is also underspecified, preventing clear attribution of any gains to the integrated design of LearnMate^2 rather than implementation differences.

    Authors: We acknowledge that greater detail on experimental controls and the baseline is required to support causal attribution. The revised manuscript will specify: random assignment of participants to conditions, a pre-study knowledge quiz used to verify group balance and control for prior knowledge variance, and task selection criteria (pilot-tested items spanning easy-to-difficult levels to reduce ceiling effects). For the baseline, we will name the state-of-the-art platform, describe the separate LLM tool configuration (including prompt templates), and contrast it with LearnMate^2's integrated design features (e.g., context-aware assistance embedded in the learning flow versus external modular tools). This will clarify the source of observed differences. revision: yes

Circularity Check

0 steps flagged

No significant circularity: empirical design and evaluation study

full rationale

The paper describes an iterative design process for an LLM-powered learning tool followed by two user studies (preliminary n=24, comparative n=16) that measure usability, learning outcomes, and user experience against baselines. No equations, fitted parameters, predictions derived from inputs, or self-citation chains appear in the provided text. Central claims rest on observed participant data and direct comparisons rather than any self-referential reduction or renaming of results. The work is therefore self-contained as an empirical HCI contribution with no load-bearing circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical derivations, free parameters, or invented entities; the work is an empirical HCI design study whose claims rest on user study outcomes rather than axioms or models.

pith-pipeline@v0.9.0 · 5480 in / 1086 out tokens · 20615 ms · 2026-05-08T07:11:12.999519+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

86 extracted references · 19 canonical work pages · 3 internal anchors

  1. [1]

    Khan Academy. 2025. Khan Academy. https://www.khanacademy.org/. Accessed: 2025-09-06

    2025

  2. [2]

    Maha Yaqoob Al Balushi and Alia Salim Al Harthi. 2024. Adaptive Learning Pathways: Advancing Personalization in Online Education Platforms. In2024 2nd International Conference on Computing and Data Analytics (ICCDA). IEEE, 1–6

    2024

  3. [3]

    Vincent Aleven, Elizabeth A McLaughlin, R Amos Glenn, and Kenneth R Koedinger. 2016. Instruction based on adaptive learning technologies. InHand- book of research on learning and instruction. Routledge, 477–518

    2016

  4. [4]

    Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz

    Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for Human- AI Interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Associa...

    work page doi:10.1145/3290605.3300233 2019

  5. [5]

    Joanne L Badge, Emma Dawson, Alan J Cann, and Jon Scott. 2008. Assessing the accessibility of online learning.Innovations in Education and Teaching Interna- tional45, 2 (2008), 103–113

    2008

  6. [6]

    Macfadyen, and Harm J.A

    Seyyed Kazem Banihashem, Omid Noroozi, Stan van Ginkel, Leah P. Macfadyen, and Harm J.A. Biemans. 2022. A systematic review of the role of learning analytics in enhancing feedback practices in higher education.Educational Research Review 37 (2022), 100489. https://doi.org/10.1016/j.edurev.2022.100489

    work page doi:10.1016/j.edurev.2022.100489 2022

  7. [7]

    Charles Bellemare, Luc Bissonnette, and Sabine Kröger. 2014. Statistical power of within and between-subjects designs in economic experiments. (2014)

    2014

  8. [8]

    Matthew L Bernacki, Meghan J Greene, and Nikki G Lobczowski. 2021. A sys- tematic review of research on personalized learning: Personalized by whom, to what, how, and for what purpose (s)?Educational Psychology Review33, 4 (2021), 1675–1715

    2021

  9. [9]

    Debra Black, Charmaine Bissessar, and Mehraz Boolaky. 2019. Online education as an opportunity equalizer: The changing canvas of online education.Interchange 50, 3 (2019), 423–443

    2019

  10. [10]

    Garvin Brod, Natalia Kucirkova, Joshua Shepherd, Dietsje Jolles, and Inge Mole- naar. 2023. Agency in educational technology: Interdisciplinary perspectives and implications for learning design.Educational Psychology Review35, 1 (2023), 25

    2023

  11. [11]

    John Brooke et al. 1996. SUS-A quick and dirty usability scale.Usability evaluation in industry189, 194 (1996), 4–7

    1996

  12. [12]

    Zhenyao Cai, Seehee Park, Nia Nixon, and Shayan Doroudi. 2024. Advancing Knowledge Together: Integrating Large Language Model-based Conversational AI in Small Group Collaborative Learning. InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI EA ’24). Association for Computing Machinery, New York, NY, USA,...

    work page doi:10.1145/3613905.3650868 2024

  13. [13]

    Yiming Cao, Zhen Li, Lizhen Cui, and Chunyan Miao. 2025. Adaptive Human- LLMs Interaction Collaboration: Reinforcement Learning driven Vision-Language Models for Medical Report Generation. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA...

    work page doi:10.1145/3706599.3719852 2025

  14. [14]

    Jiaju Chen, Minglong Tang, Yuxuan Lu, Bingsheng Yao, Elissa Fan, Xiaojuan Ma, Ying Xu, Dakuo Wang, Yuling Sun, and Liang He. 2025. Characterizing LLM- Empowered Personalized Story Reading and Interaction for Children: Insights From Multi-Stakeholder Perspectives. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Ass...

    work page arXiv 2025

  15. [15]

    Lijia Chen, Pingping Chen, and Zhijian Lin. 2020. Artificial intelligence in education: A review.IEEE access8 (2020), 75264–75278

    2020

  16. [16]

    Liuqing Chen, Shuhong Xiao, Yunnong Chen, Yaxuan Song, Ruoyu Wu, and Lingyun Sun. 2024. ChatScratch: An AI-Augmented System Toward Autonomous Visual Programming Learning for Children Aged 6-12. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA) (CHI ’24). Association for Computing Machinery, New York, NY, USA...

    work page doi:10.1145/3613904.3642229 2024

  17. [17]

    Yu-Jung Chung, Chen-Wei Hsu, Meng-Hsun Chan, and Fu-Yin Cherng. 2024. Enhancing ESL Learners’ Experience and Performance through Gradual Adjust- ment of Video Speed during Extensive Viewing. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery, New York, NY, USA, Ar...

    work page doi:10.1145/3613904.3642366 2024

  18. [18]

    Victoria Clarke and Virginia Braun. 2014. Thematic analysis. InEncyclopedia of critical psychology. Springer, 1947–1952

    2014

  19. [19]

    Allan Collins, John Seely Brown, Ann Holum, et al. 1991. Cognitive apprentice- ship: Making thinking visible.American educator15, 3 (1991), 6–11

    1991

  20. [20]

    Coursera. 2026. Coursera. https://www.coursera.org/. Accessed: 2026-04-09

    2026

  21. [21]

    John Daniel. 2012. Making sense of MOOCs: Musings in a maze of myth, paradox and possibility.Journal of interactive Media in education2012, 3 (2012), 18–18

    2012

  22. [22]

    Google DeepMind. 2025. Gemini. https://deepmind.google/technologies/gemini/. Accessed: 2025-09-06

    2025

  23. [23]

    Vanessa Paz Dennen. 2013. Cognitive apprenticeship in educational practice: Research on scaffolding, modeling, mentoring, and coaching as instructional strategies. InHandbook of research on educational communications and technology. Routledge, 804–819

    2013

  24. [24]

    Michelle Deschênes. 2020. Recommender systems to support learners’ Agency in a Learning Context: a systematic review.International journal of educational technology in higher education17, 1 (2020), 50

    2020

  25. [25]

    Do, Usama Bin Shafqat, Elsie Ling, and Nikhil Sarda

    Tiffany D. Do, Usama Bin Shafqat, Elsie Ling, and Nikhil Sarda. 2025. PAIGE: Examining Learning Outcomes and Experiences with Personalized AI-Generated Educational Podcasts. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 896, 12 pages. https://doi.or...

    work page doi:10.1145/3706598.3713460 2025

  26. [26]

    Upol Ehsan, Q Vera Liao, Michael Muller, Mark O Riedl, and Justin D Weisz

  27. [27]

    In Proceedings of the 2021 CHI conference on human factors in computing systems

    Expanding explainability: Towards social transparency in ai systems. In Proceedings of the 2021 CHI conference on human factors in computing systems. 1–19

    2021

  28. [28]

    O Elwarraki, S Aammou, Youssef Jdidou, and Jalal Lahiassi. 2023. Toward the future of personalized learning: Emerging trends and challenges in recommenda- tion systems.ICERI2023 Proceedings(2023), 7226–7235

    2023

  29. [29]

    Haoxiang Fan, Guanzheng Chen, Xingbo Wang, and Zhenhui Peng. 2024. Lesson- Planner: Assisting novice teachers to prepare pedagogy-driven lesson plans with large language models. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology. 1–20

    2024

  30. [30]

    Dhananjaya. G. M., R. H. Goudar, Anjanabhargavi A. Kulkarni, Vijayalaxmi N. Rathod, and Geetabai S. Hukkeri. 2024. A Digital Recommendation System for Personalized Learning to Enhance Online Education: A Review.IEEE Access12 (2024), 34019–34041. https://doi.org/10.1109/ACCESS.2024.3369901

    work page doi:10.1109/access.2024.3369901 2024

  31. [31]

    Meiyuzi Gao, Philip Kortum, and Frederick Oswald. 2018. Psychometric eval- uation of the use (usefulness, satisfaction, and ease of use) questionnaire for reliability and validity. InProceedings of the human factors and ergonomics so- ciety annual meeting, Vol. 62. SAGE Publications Sage CA: Los Angeles, CA, 1414–1418

    2018

  32. [32]

    Jenna Gillett-Swan. 2017. The challenges of online learning: Supporting and engaging the isolated learner.Journal of learning design10, 1 (2017), 20–30

    2017

  33. [33]

    Ilie Gligorea, Marius Cioca, Romana Oancea, Andra-Teodora Gorski, Hortensia Gorski, and Paul Tudorache. 2023. Adaptive learning using artificial intelligence in e-learning: A literature review.Education Sciences13, 12 (2023), 1216

    2023

  34. [34]

    Charles R Graham, Jered Borup, Cecil R Short, and Leanna Archambault. 2019. K-12 blended teaching: A guide to personalized learning and online integration. Provo, UT: EdTechBooks(2019)

    2019

  35. [35]

    Stephen Grossberg. 2020. A path toward explainable AI and autonomous adap- tive intelligence: Deep learning, adaptive resonance, and models of perception, emotion, and action.Frontiers in neurorobotics14 (2020), 36

    2020

  36. [36]

    Bui Phu Hung and Loc Tan Nguyen. 2022. Scaffolding language learning in the online classroom.New trends and applications in Internet of things (IoT) and big data analytics(2022), 109–122

    2022

  37. [37]

    Fumiya Iida and Fabio Giardina. 2023. On the timescales of embodied intelli- gence for autonomous adaptive systems.Annual Review of Control, Robotics, and Autonomous Systems6, 1 (2023), 95–122

    2023

  38. [38]

    Muhammad Imran, Norah Almusharraf, Saim Ahmed, and Muhammad Ismail Mansoor. 2024. Personalization of E-Learning: Future Trends, Opportunities, and Challenges.International Journal of Interactive Mobile Technologies18, 10 (2024)

    2024

  39. [39]

    Francisco Iniesto and Covadonga Rodrigo. 2024. Understanding accessibility in MOOCS: findings and recommendations for future designs.Journal of Interactive Media in Education2024, 1 (2024), 20

    2024

  40. [40]

    Majeed Kazemitabaar, Runlong Ye, Xiaoning Wang, Austin Zachary Henley, Paul Denny, Michelle Craig, and Tovi Grossman. 2024. CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). As...

    work page doi:10.1145/3613904.3642773 2024

  41. [41]

    Deepak Kem. 2022. Personalised and adaptive learning: Emerging learning platforms in the era of digital and smart learning.International Journal of Social Science and Human Research5, 2 (2022), 385–391

    2022

  42. [42]

    Kenneth R Koedinger and Vincent Aleven. 2007. Exploring the assistance dilemma in experiments with cognitive tutors.Educational psychology review19, 3 (2007), 239–264

    2007

  43. [43]

    Todd Kulesza, Margaret Burnett, Weng-Keen Wong, and Simone Stumpf. 2015. Principles of explanatory debugging to personalize interactive machine learning. InProceedings of the 20th international conference on intelligent user interfaces. 126–137

    2015

  44. [44]

    Poonam Kumar, Anil Kumar, Shailendra Palvia, and Sanjay Verma. 2019. Online business education research: Systematic analysis and a conceptual model.The International Journal of Management Education17, 1 (2019), 26–35

    2019

  45. [45]

    Christine P Lee, Min Kyung Lee, and Bilge Mutlu. 2024. The AI-DEC: a card-based design method for user-centered AI explanations. InProceedings of the 2024 ACM Designing Interactive Systems Conference. 1010–1028

    2024

  46. [46]

    Christine P Lee, David Porfirio, Xinyu Jessica Wang, Kevin Chenkai Zhao, and Bilge Mutlu. 2025. VeriPlan: Integrating formal verification and LLMs into end- user planning. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems. 1–19

    2025

  47. [47]

    Christine P Lee, Xinyu Jessica Wang, Aws Albarghouthi, David Porfirio, and Bilge Mutlu. 2026. U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning. arXiv:2605.02765 [cs.AI] https://arxiv.org/abs/2605. 02765

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  48. [48]

    Joanne Leong, Pat Pataranutaporn, Valdemar Danry, Florian Perteneder, Yaoli Mao, and Pattie Maes. 2024. Putting things into context: Generative AI-enabled context personalization for vocabulary learning improves learning motivation. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1–15

    2024

  49. [49]

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems33 (2020), 9459–9474

    2020

  50. [50]

    Fengying Li, Yifeng He, and Qingshui Xue. 2021. Progress, challenges and countermeasures of adaptive learning.Educational Technology & Society24, 3 (2021), 238–255

    2021

  51. [51]

    Effie Maclellan. 2014. How might teachers enable learner self-confidence? A review study.Educational Review66, 1 (2014), 59–74

    2014

  52. [52]

    Uwe Maier and Christian Klotz. 2022. Personalized feedback in digital learning environments: Classification framework and literature review.Computers and education: Artificial intelligence3 (2022), 100080

    2022

  53. [53]

    Florence Martin, Yan Chen, Robert L Moore, and Carl D Westine. 2020. Systematic review of adaptive learning research designs, context, strategies, and technologies from 2009 to 2018.Educational Technology Research and Development68, 4 (2020), 1903–1929

    2020

  54. [54]

    Nora McDonald, Sarita Schoenebeck, and Andrea Forte. 2019. Reliability and Inter-rater Reliability in Qualitative Research: Norms and Guidelines for CSCW and HCI Practice.Proceedings of the ACM on Human-Computer Interaction3 (11 2019), 1–23. https://doi.org/10.1145/3359174

    work page doi:10.1145/3359174 2019

  55. [55]

    Meta Platforms, Inc. 2013. React – A JavaScript library for building user interfaces. https://reactjs.org/. Accessed: 2025-09-11

    2013

  56. [56]

    Sein Minn. 2022. AI-assisted knowledge assessment techniques for adaptive learning environments.Computers and Education: Artificial Intelligence3 (2022), 100050

    2022

  57. [57]

    William H Money and Benjamin P Dean. 2019. Incorporating student population differences for effective online education: A content-based review and integrative model.Computers & Education138 (2019), 57–82

    2019

  58. [58]

    Mir Murtaza, Yamna Ahmed, Jawwad Ahmed Shamsi, Fahad Sherwani, and Mariam Usman. 2022. AI-based personalized e-learning systems: Issues, chal- lenges, and solutions.IEEE access10 (2022), 81323–81342

    2022

  59. [59]

    Alaeddin Nassani, John Blake, and Julian Villegas. 2025. Adaptive Learning Companions: Enhancing Education with Biosignal-Driven Digital Human. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, Article 63, 7 pages. https://doi.org/10.11...

    work page doi:10.1145/3706599.3719877 2025

  60. [60]

    OnTask. 2026. OnTask. https://www.ontasklearning.org/. Accessed: 2026-04-09

    2026

  61. [61]

    Bens Pardamean, Teddy Suparyanto, Tjeng Wawan Cenggoro, Digdo Sudigyo, and Andri Anugrahana. 2022. AI-based learning style prediction in online learning for primary education.Ieee Access10 (2022), 35725–35735

    2022

  62. [62]

    Minju Park, Sojung Kim, Seunghyun Lee, Soonwoo Kwon, and Kyuseok Kim

  63. [63]

    InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems

    Empowering personalized learning through a conversation-based tutoring system with student modeling. InExtended Abstracts of the CHI Conference on Human Factors in Computing Systems. 1–10

  64. [64]

    Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis.arXiv preprint arXiv:2307.16789(2023)

    work page internal anchor Pith review arXiv 2023

  65. [65]

    Jason Quense. n.d.. React Big Calendar. https://github.com/jquense/react-big- calendar Accessed: 2025-01-24

    2025

  66. [66]

    Emilee Rader, Kelley Cotter, and Janghee Cho. 2018. Explanations as mechanisms for supporting algorithmic transparency. InProceedings of the 2018 CHI conference on human factors in computing systems. 1–13

    2018

  67. [67]

    Lin, Emma Anderson, Matt Taylor, Anastasia K

    Prerna Ravi, John Masla, Gisella Kakoti, Grace C. Lin, Emma Anderson, Matt Taylor, Anastasia K. Ostrowski, Cynthia Breazeal, Eric Klopfer, and Hal Abelson

  68. [68]

    InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25)

    Co-designing Large Language Model Tools for Project-Based Learning with K12 Educators. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 138, 25 pages. https://doi.org/10.1145/3706598.3713971

    work page doi:10.1145/3706598.3713971 2025

  69. [69]

    Mohi Reza, Juho Kim, Ananya Bhattacharjee, Anna N Rafferty, and Joseph Jay Williams. 2021. The MOOClet framework: unifying experimentation, dynamic improvement, and personalization in online courses. InProceedings of the eighth acm conference on learning@ scale. 15–26

    2021

  70. [70]

    Sherry Ruan, Liwei Jiang, Justin Xu, Bryce Joe-Kun Tham, Zhengneng Qiu, Yeshuang Zhu, Elizabeth L Murnane, Emma Brunskill, and James A Landay. 2019. Quizbot: A dialogue-based adaptive learning system for factual knowledge. In Proceedings of the 2019 CHI conference on human factors in computing systems. 1–13

    2019

  71. [71]

    Atikah Shemshack and Jonathan Michael Spector. 2020. A systematic literature review of personalized learning terms.Smart learning environments7, 1 (2020), 33

    2020

  72. [72]

    Ashraful Amin, and Amin Ahsan Ali

    Muhtasim Ibteda Shochcho, Mohammad Ashfaq Ur Rahman, Shadman Rohan, Ashraful Islam, Hasnain Heickal, AKM Mahbubur Rahman, M. Ashraful Amin, and Amin Ahsan Ali. 2025. Improving User Engagement and Learning Outcomes in LLM-Based Python Tutor: A Study of PACE. InProceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems...

    work page doi:10.1145/3706599.3720240 2025

  73. [73]

    Edlir Spaho, Betim Çiço, and Isak Shabani. 2025. IoT Integration Approaches into Personalized Online Learning: Systematic Review.Computers14, 2 (2025), 63

    2025

  74. [74]

    Jenny Spouse. 1998. Scaffolding student learning inclinical practice.Nurse Education Today18, 4 (1998), 259–266. https://doi.org/10.1016/S0260-6917(98) 80042-7

    work page doi:10.1016/s0260-6917(98 1998

  75. [75]

    Karen Swan. 2003. Learning effectiveness online: What the research tells us. Elements of quality online education, practice and direction4, 1 (2003), 13–47

    2003

  76. [76]

    Keith S Taber. 2018. Scaffolding learning: Principles for effective teaching and the design of classroom resources.Effective teaching and learning: Perspectives, strategies and implementation(2018), 1–43

    2018

  77. [77]

    Yilin Tang, Liuqing Chen, Ziyu Chen, Wenkai Chen, Yu Cai, Yao Du, Fan Yang, and Lingyun Sun. 2024. EmoEden: Applying Generative Artificial Intelligence to Emotional Learning for Children with High-Function Autism. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems(Honolulu, HI, USA)(CHI ’24). Association for Computing Machinery...

    work page doi:10.1145/3613904.3642899 2024

  78. [78]

    Department of Education

    U.S. Department of Education. 2010.Transforming American education: learning powered by technology. Technical Report. Office of Educational Technology, Washington, DC

    2010

  79. [79]

    Mieke Vandewaetere, Piet Desmet, and Geraldine Clarebout. 2011. The contribu- tion of learner characteristics in the development of computer-based adaptive learning environments.Computers in Human Behavior27, 1 (2011), 118–130

    2011

  80. [80]

    George Veletsianos and Shandell Houlden. 2019. An analysis of flexible learning and flexibility over the last 40 years of Distance Education.Distance Education 40, 4 (2019), 454–468

    2019

Showing first 80 references.