CogniLeapAI: An Adaptive Personalized Learning Platform with AI-Powered Content Generation, Active Recall, and Intelligent Study Planning

Year : 2026 | Volume : 13 | Issue : 02 | Page : 45 63
By

Swami Yogesh Wagh,

Udaysing Bharatsing Rajput,

Darshan Vinod Agrawal,

Sarthak Kiran Khairate,

C.N. Patki,

  1. Assistant Professor, Department of Computer Engineering, SVPM’s College of Engineering, Maharashtra, India
  2. Assistant Professor, Department of Computer Engineering, SVPM’s College of Engineering, Maharashtra, India
  3. Assistant Professor, Department of Computer Engineering, SVPM’s College of Engineering, Maharashtra, India
  4. Assistant Professor, Department of Computer Engineering, SVPM’s College of Engineering, Maharashtra, India
  5. Student, Department of Computer Engineering, SVPM’s College of Engineering, Maharashtra, India

Abstract

Students today must work through large volumes of academic PDFs with little tooling to support effective learning. Passive reading remains the default approach for most learners, yet it consistently produces poor retention and demands excessive preparation time. This paper presents CogniLeapAI, a web-based platform designed to convert static PDF documents into a closed-loop adaptive learning system. AI requests are routed across four providers (Google Gemini, OpenRouter, LaoZhang, and Kie.ai) with intelligent fallback chains and user-configurable encrypted API keys. From any uploaded document, six study tool types can be generated: summaries, study guides, notes, flashcards, interactive quizzes, and node-based mind maps. Retention is managed through a four-layer SM-2 spaced-repetition framework (Absorb, Recognize, Retrieve, Mastered), with AI-adjusted review intervals, response-time-aware scheduling, post-session weakness scoring, and predictive retention forecasting. An Adaptive AI Study Agent handles exam-aware plan generation, produces weekly learning reports, and adjusts schedules in real-time based on per-topic card data and stuck-card detection. The backend runs on Next.js 15, React 19, and Supabase, with AES-256-GCM key storage, row-level security, and per-request cost tracking built in. Field testing showed measurable time savings in study material preparation, stronger learner engagement through active recall, and improved long-term retention relative to passive document reading.

Keywords: Educational technology, multi-model AI integration, document processing, study material generation, spaced repetition, active recall, AI study agent, personalized learning, predictive analytics

[This article belongs to Journal of Software Engineering Tools & Technology Trends ]

How to cite this article: Swami Yogesh Wagh, Udaysing Bharatsing Rajput, Darshan Vinod Agrawal, Sarthak Kiran Khairate, C.N. Patki. CogniLeapAI: An Adaptive Personalized Learning Platform with AI-Powered Content Generation, Active Recall, and Intelligent Study Planning. Journal of Software Engineering Tools & Technology Trends. 2026; 13(02):45-63.
How to cite this URL: Swami Yogesh Wagh, Udaysing Bharatsing Rajput, Darshan Vinod Agrawal, Sarthak Kiran Khairate, C.N. Patki. CogniLeapAI: An Adaptive Personalized Learning Platform with AI-Powered Content Generation, Active Recall, and Intelligent Study Planning. Journal of Software Engineering Tools & Technology Trends. 2026; 13(02):45-63. Available from: https://journals.stmjournals.com/josettt/article=2026/view=259426

References

  1. Pirjan A, Petrosanu DM. Exploring large language models in the education process with a view towards transforming personalized learning. J Inf Syst Oper Manag. 2024;18:125–71.
  2. Balaji N, Kumari D, Bhavatarini N, Megha N, Kumar S. Text summarization using NLP technique. In: Proceedings of the 2022 International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER); 2022. p. 30–5.
  3. Puvvadi M, Arava SK, Santoria A, Chennupati SSP, Puvvadi HV. Generative AI for personalized learning and education. In: Proceedings of the 7th International Conference on Intelligent Sustainable Systems (ICISS); 2025. p. 1621–7. doi:10.1109/ICISS63372.2025.11076239.
  4. Chen S, Liu Q, He B. A generative AI-based teaching material system using a human-in-the-loop model. In: Proceedings of the International Conference on Intelligent Education and Intelligent Research (IEIR); 2023. p. 1–8. doi:10.1109/IEIR59294.2023.10391244.
  5. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. Adv Neural Inf Process Syst. 2017;30.
  6. Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst. 2020;33:9459–74.
  7. Woźniak PA, Gorzelańczyk EJ. Optimization of repetition spacing in the practice of learning. Acta Neurobiol Exp (Wars). 1994;54:59–62. doi:10.55782/ane-1994-1003. PMID:8023714.
  8. Latimier A, Peyre H, Ramus F. A meta-analytic review of the benefit of spacing out retrieval practice episodes on retention. Educ Psychol Rev. 2021;33:959–87. doi:10.1007/s10648-020-09572-8.
  9. Karpicke JD, Roediger HL III. The critical importance of retrieval for learning. Science. 2008;319:966–8. doi:10.1126/science.1152408. PMID:18276894.
  10. Dunlosky J, Rawson KA, Marsh EJ, Nathan MJ, Willingham DT. Improving students’ learning with effective learning techniques: promising directions from cognitive and educational psychology. Psychol Sci Public Interest. 2013;14:4–58. doi:10.1177/1529100612453266. PMID:26173288.
  11. Paddags B, Hershcovich D, Savage V. Automated sentence generation for a spaced repetition software. In: Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA); 2024. p. 351–64.
  12. Tural B, Örpek Z, Destan Z. Retrieval-augmented generation (RAG) and LLM integration. In: Proceedings of the 8th International Symposium on Innovative Approaches in Smart Technologies (ISAS); 2024. p. 1–5. doi:10.1109/ISAS64331.2024.10845308.
  13. Team G, Georgiev P, Lei VI, Burnell R, Bai L, Gulati A, et al. Unlocking multimodal understanding across millions of tokens of context [Preprint]. 2024 Mar 8. arXiv:2403.05530.
  14. Chen L, Zaharia M, Chen ZJ. FrugalGPT: how to use large language models while reducing cost and improving performance [Preprint]. 2023 May 9. arXiv:2305.05176.
  15. Ong I, Almahairi A, Wu V, Chiang WL, Wu T, Gonzalez JE, et al. RouteLLM: learning to route LLMs with preference data [Preprint]. 2024. arXiv:2406.18665.
  16. Huang J, Zhong Y, Chen X. Adaptive and personalized learning in STEM education using high-performance computing and artificial intelligence. J Supercomput. 2025;81:981. doi:10.1007/s11227-025-07481-7.
  17. Nguyen A, Ngo HN, Hong Y, Dang B, Nguyen BT. Ethical principles for artificial intelligence in Educ Inf Technol. 2023;28:4221–41. doi:10.1007/s10639-022-11316-w. PMID:36254344.
  18. Thabet B, Zanichelli N, Zanichelli F. Transformer-based recommender enabling automatic flashcards generation. In: Book of abstracts: 4th International Conference on Higher Education Learning Methodologies and Technologies Online (HELMeTO 2022); 2022 Sep 21-23; Palermo, Italy. p. 222-5.
  19. Henry MM, Heryanto NA, Isnan M, Nugroho KS, Pardamean B. Automatic multiple choice question generation: a systematic literature review. In: Proceedings of the 9th International Conference on Information Technology and Digital Applications (ICITDA); 2024. p. 1–7. doi:10.1109/ICITDA64560.2024.10810102.
  20. Pawar P, Dube R, Joshi A, Gulhane Z, Patil R. Automated generation and evaluation of multiple-choice quizzes using LangChain and Gemini LLM. In: Proceedings of the International Conference on Electrical, Electronics and Computing Technologies (ICEECT). Vol. 1; 2024. p. 1–7. doi:10.1109/ICEECT61758.2024.10739326.

 

Regular Issue Subscription Original Research
Volume 13
Issue 02
Received 05/05/2026
Accepted 16/07/2026
Published 10/08/2026
Publication Time 97 Days

Login

My IP

PlumX Metrics

Support