AI summary · arXiv: 2509.13348v1 · cs.CY
Towards an AI-Augmented Textbook
The essentials
- Study titled "Towards an AI-Augmented Textbook" by the LearnLM Team from Google
- Introduces system called Learn Your Way for transforming traditional textbooks using generative AI
- Addresses limitations of one-size-fits-all textbooks through layers of multiple representations and personalization
- System allows scalable adaptations of textbook content with minimal human effort
- Pedagogical evaluations and randomized control trial conducted to compare learning outcomes between Learn Your Way and traditional methods
- Significant advantages in learning with Learn Your Way observed over traditional textbook usage
- Revolutionizes educational materials by enhancing content integrity, quality, and providing personalized learning experiences
- Sets a new standard for adaptive and personalized education through innovative technology integration
Key points written by AI: they may contain errors, check them against the paper.
Ask questions about this paper to our AI assistant
How to chat with this paper? Illustrated guide
You can also chat with multiple papers at once here.
Keep this conversation — a free account saves your questions and answers, your collections of papers and your alerts.
Continue with Google Create a free accountTools for this paper
Advanced tools Premium
For researchers who follow a field closely: citation alerts, journal-club slides, version comparison and Zotero export. Discover Premium
Papers around this one
See them on a mapRanked by how close their title and abstract are to this paper’s. Select some to read them together.
Closest papers
-
GenAIReading: Augmenting Human Cognition with Interactive Digital Textbooks Using Large Language Models and Image Generation ModelsRyugo Morita, Kousuke Watanabe, Jin-Jia Zhou et al. · 2025 · NASA/ESA Conference on Adaptive Hardware and Systems · cited 19 times · Not summarized yet
GenAIReading uses language and image generation models to add summaries and aligned visuals to textbooks, while this paper transforms and personalizes textbook material.
Abstract
Cognitive augmentation is a cornerstone in advancing education, particularly through personalized learning. However, personalizing extensive textual materials, such as narratives and academic textbooks, remains challenging due to their heavy use, which can hinder learner engagement and understanding. Building on cognitive theories like Dual Coding Theory—which posits that combining textual and visual information enhances comprehension and memory—this study explores the potential of Generative AI (GenAI) to enrich educational materials. We utilized large language models (LLMs) to generate concise text summaries and image generation models (IGMs) to create visually aligned content from textual…
-
An experimental evaluation of an AI-powered interactive learning platformCourtney Heldreth, Diana Akrong, Laura M. Vardoulakis et al. · 2025 · Frontiers Artif. Intell. · Not summarized yet
An experimental evaluation tests Learn Your Way’s textbook transformations through a study with 60 students; it cites this paper.
Abstract
Generative AI, which is capable of transforming static content into dynamic learning experiences, holds the potential to revolutionize student engagement in educational contexts. However, questions still remain around whether or not these tools are effective at facilitating student learning. In this research, we test the effectiveness of an AI-powered platform incorporating multiple representations and assessment through Learn Your Way, an experimental research platform that transforms textbook chapters into dynamic visual and audio representations. Through a between-subjects, mixed methods experiment with 60 US-based students, we demonstrate that students who used Learn Your Way had a more …
-
Empowering Education by Developing and Evaluating Generative AI-Powered Tutoring System for Enhanced Student LearningShivraj Banjade, Hiran Patel, Sangita Pokhrel · 2024 · Journal of Artificial Intelligence and Capsule Networks · cited 33 times · Not summarized yet
The tutoring system uses generative AI to create lesson resources and personalize learning, rather than focusing on transforming textbooks.
Abstract
Personalized learning has always been a dream for schools, educators, and students but until recently, educators didn’t have the time or resources to implement it on a large scale. With the advancements in AI, Generative AI can automate many of a teacher’s core tasks, such as creating lesson resources. providing lesson structures and key talking points, designing infographics, creating slideshows, and converting text into videos and images. This study details the development and evaluation of an AI-powered tutoring system designed to enhance student learning experiences. Motivated by the transformative potential of AI in education, the research aims to utilize large language models, includin…
-
Generative AI for Education: A Retrieval-Augmented System for Effective Feedback in Self-AssessmentJuan Martínez-Romo, Lourdes Araujo, Laura Plaza et al. · 2025 · IEEE Global Engineering Education Conference · cited 3 times · Not summarized yet
The RAG system grounds personalized self-assessment feedback in textbook material, whereas this paper augments textbooks with new representations.
Abstract
The application of generative AI in education has shown significant potential to enhance learning outcomes by providing personalized, adaptive feedback to students. In this work, we present a novel Retrieval-Augmented Generation (RAG) system designed to improve the explanations and feedback provided to students during self-assessment activities. The system we developed is grounded in the course's reference material, ensuring that the feedback remains accurate, consistent, and contextually relevant to the student's curriculum. The system retrieves information directly from the textbook, reducing ambiguity and interpretation errors, and generates responses tailored to the specific needs of eac…
-
AdaptLearn AI: A Generative AI Framework for Bidirectional Personalization in EducationShuryansh Gupta, Sanjay Tiwari, M. Arya et al. · 2025 · 2025 International Conference on Computing, Intelligence, and Application (CIACON) · cited 2 times · Not summarized yet
AdaptLearn AI combines teacher support with personalized student content, while this paper focuses on scalable textbook transformations.
Abstract
Teacher burnout and student disengagement are twin crises crippling modern education, with 72% of educators overwhelmed by administrative tasks and 61% of students underserved by one-size-fits-all curricula. While generative AI tools like GPT-4 offer transformative potential, existing systems address only isolated needs—automating grading or personalizing content, but never both. This paper introduces AdaptLearn AI, the first framework to unify teacher support and student adaptation through bidirectional generative AI. Our architecture combines fine-tuned Large Large Language Models(LLMs) for dynamic content generation (e.g., adjusting STEM problems via few-shot learning) with Retrieval-Augm…
-
Teaching with Generative AI: moving forward with content creationT. Ullmann, Duygu Bektik, Chris Edwards et al. · 2024 · Ubiquity Proceedings · cited 11 times · Not summarized yet
This paper evaluates expert-reviewed AI-generated course content, addressing educational content creation rather than textbook augmentation for learners.
Abstract
Generative AI is widely available and has raised the expectation that it will impact Education. Models, such as ChatGPT, can quickly produce plausible texts on a wide range of topics, and this capability may be of potential use in course content production. This paper selects several important course content production tasks, describes the prompts used, and assesses the quality of the automatically generated texts by a team of experts. Across all tasks, the Generative AI produced content that could help solve specific tasks by aiding with brainstorming, creating outlines, and adhering to particular writing guidance. In all cases, the content required adjustments and checking by human experts…
-
Harmonizing Assistance: Moderating Visual and Textual Aids in AI-Enhanced Textbook Reading with IReadXiaoyu Zhang, Vincent Dörig, Peng Cui et al. · 2025 · International Journal of Artificial Intelligence in Education · cited 1 time · Not summarized yet
IRead balances visual and textual support during textbook reading, while this paper adds personalized representations to textbook content.
Abstract
Textbooks continue to be one of primary mediums of learning. Students often need additional support during the process of reading textbooks, leading to several research efforts that aim to increase student engagement and provide tailored experiences in textbook reading. However, providing excessive information beyond the textbook can also distract students from the reading task. When enhancing the reading experience, one has to strike a delicate balance between providing sufficient informational support and maintaining students’ focus on textbook reading. Fusing together latest developments in large language models (LLMs) and their applications in education and several pedagogical theories, …
-
Generative AI in Teaching and Learning: Benefits and ChallengesUmesh Silwal, R. Kafle, Ramesh Dhungana · 2025 · Journal of Nepal Physical Society · cited 1 time · Not summarized yet
This article surveys generative AI tools, classroom uses, ethical considerations, and challenges in teaching and learning.
Abstract
Recent advancements in Artificial Intelligence (AI), particularly Generative AI (GenAI), have brought both transformative opportunities and significant challenges to the future of teaching and learning practices. This article provides an overview of popular GenAI tools and explores strategies for integrating them into classroom instructions, their ethical considerations, and challenges. This work includes narratives of implementation demonstrating how specific GenAI tools were utilized by the authors, including the use of ChatGPT for drafting an assignment, NotebookLM for curating content, developing formative assessments, and providing study materials for students, and the application of AI…
Prior work it builds on
-
Instruction Based on Adaptive Learning TechnologiesV. Aleven, Elizabeth Mclaughlin, A. Glenn et al. · 2016 · cited 273 times · Not summarized yet
Instruction Based on Adaptive Learning Technologies is cited as background for this paper’s work on adapting learning materials.
-
Assessment as Learning: Using Classroom Assessment to Maximize Student LearningL. Earl · 2003 · cited 920 times · Not summarized yet
Assessment as Learning is cited as educational background for this paper’s evaluation of learning with augmented textbooks.
-
Personalization through Adaptivity or Adaptability? A Meta-analysis on Simulation-based Learning in Higher EducationO. Chernikova, D. Sommerhoff, Matthias Stadler et al. · 2024 · Educational Research and Reviews · cited 42 times · Not summarized yet
This meta-analysis compares adaptivity and learner-controlled adaptability in simulation-based learning; this paper cites it when framing personalization.
Abstract
This meta-analysis builds on 217 empirical studies in higher education and investigates the role of the different forms of adaptivity and adaptability as personalization strategies in simulation-based learning environments for complex skills in higher education. The strategies used to personalize scaffolding and task progression were the central point in this meta-analysis. We identified conditions under which personalization advances complex skills in higher education. The results indicate that whereas adaptivity (i.e., computer makes decisions) is more effective for scaffolding, adaptability (the decisions made by individual learners) seem more beneficial for task progression. We conclude …
-
A Systematic Review of Research on Personalized Learning: Personalized by Whom, to What, How, and for What Purpose(s)?Matthew L. Bernacki, Meghan J. Greene, Nikki G. Lobczowski · 2021 · Educational Psychology Review · cited 433 times · Not summarized yet
This systematic review surveys personalized learning by who personalizes, what is adapted, how, and for what purposes; this paper cites it.
-
Toward a taxonomy of adaptivity for learningJ. Plass, S. Pawar · 2020 · Journal of Research on Technology in Education · cited 185 times · Not summarized yet
Toward a taxonomy of adaptivity defines personalization concepts and adaptation variables, providing cited background for this paper.
Abstract
Abstract Adaptive learning and personalization have long been of great interest to learning designers and educators, and recent technological advances that have opened up a range of new possibilities for adaptivity. However, we lack clear definitions of the terms adaptivity and personalization, and the theoretical and empirical soundness of implementations of corresponding systems varies greatly. We therefore first provide definitions for key concepts related to adaptivity. We then discuss what variable systems should adapt for, how these variables can be measured, and what modifications to the learner experience can be made based on these variables. We propose a taxonomy of adaptivity that …
Papers that cite it
-
A Semi-Automated System for Generating Dialogue-Based TTS Lessons Using Large Language Models: An Exploratory Study of Educational PotentialG. Kumoi, Fumie Watanabe, Tota Suko et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 2 times · Not summarized yet
This study uses LLMs and text-to-speech to generate audiovisual lessons, applying AI-generated educational representations beyond textbooks; it cites this paper.
Abstract
This study proposes a semi-automated system for generating dialogue-based lessons using Large Language Models (LLMs) and Text-to-Speech (TTS) technology, and exploratorily examines its educational potential via a practical quasi-experiment. The system augments rather than replaces educators through a three-stage human-in-the-loop workflow (LLM-based slide/narration generation, educator review, automated audiovisual integration), and introduces a novel method for generating Expert-Novice dialogue narration based on cognitive apprenticeship theory. In a study of 245 first-year high school students who sequentially experienced three lesson formats (instructor voice, single-speaker TTS, dialogue…
-
DeepTutor: Towards Agentic Personalized TutoringBin Zhao, Jiahao Zhang, Xubin Ren et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 2 times · Not summarized yet
DeepTutor personalizes learning with LLM agents, learner memory, and grounded content, extending generative AI personalization to tutoring; it cites this paper.
Abstract
Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to individual learners, while existing RAG systems fall short in delivering personalized, guided feedback. To bridge this gap, we present DeepTutor, a fully open-source agentic framework that unifies citation-grounded problem tutoring with difficulty-calibrated question generation. A hybrid personalization engine couples static knowledge grounding with dynamic learner memory, continuously adapting each interaction to the student's evolving needs. The same personalization substrate further extends to adaptive learning …
-
Greenwashing AI in Higher Ed: An environmental argument for universities’ resistance to Big TechMatt Riemland · 2026 · Open Research Europe · Not summarized yet
This essay examines the environmental harms of commercial AI in higher education and cites this paper as an example of AI use in education.
Abstract
Higher education’s (“Higher Ed”) rushed embrace of commercial AI technologies has not allowed for sufficient reflection on their serious ecological consequences. This issue is complicated by Big Tech corporations becoming increasingly intertwined in university ecosystems while profiting enormously from AI expansion. As a contribution to Open Research Europe’s Universities for Sustainability collection, this essay explores universities’ potential actions in response to AI’s growing environmental harms, urging higher education institutions (HEIs) to resist Big Tech’s encroachment into the sector. First, the paper outlines the increasing entanglements between universities and Big Tech. It then …
Go further
How are these papers found?
We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.
Updated on 31 October 2026.
The previous summary was created more than a year ago and can be re-run (if necessary) by clicking on the Run button below.
Disclaimer: The AI-based summarization tool and virtual assistant provided on this website may not always provide accurate and complete summaries or responses. We encourage you to carefully review and evaluate the generated content to ensure its quality and relevance to your needs.