Descriptive – Product Development

Takeaways

Integrating human oversight with AI tools through collaborative design processes involving teachers in development and review stages ensures educational tools align with curriculum objectives and pedagogical needs while maintaining appropriate human judgment (Sonkar et al. (2024), Clark et al. (2025), Baffour et al. (2024)).
Retrieval-Augmented Generation (RAG) significantly improves the accuracy and reliability of AI-generated educational content by grounding responses in verified textbooks, curriculum materials, and reliable sources (Kloker et al. (2024), Forootani et al. (2024), Hu & Wang (2024)).
Simulation-based learning environments powered by AI enable students to practice skills in authentic scenarios without real-world consequences, allowing for experimentation, failure, and iterative improvement (Mollick et al. (2024), Ben-Zion et al. (2024), Mollick & Mollick (2024)).
AI assessment tools demonstrate the highest accuracy and educational value when they evaluate multiple dimensions of student work (not just correctness), provide specific feedback for improvement, and maintain alignment with learning objectives (Baral et al. (2024), Xie et al. (2024)).
Addressing bias in AI educational tools requires diverse representation in training datasets, ongoing evaluation with varied stakeholder input, and systematic review processes to ensure equitable learning experiences for all students (Makridis et al. (2024), Eloundou et al. (2025), Baffour et al. (2024)).

Research synthesis is AI-generated, human reviewed. Updated 03/2025.

Displaying 1 - 30 of 138

How Do Teachers Create Pedagogical Chatbots?: Current Practices and Challenges

Minju Yoo, Hyoungwook Jin, Juho Kim. (03/2025). arXiv. https://arxiv.org/pdf/2503.00967
Use Me Wisely: Al-Driven Assessment for LLM Prompting Skills Development

Dimitri Ognibene, Gregor Donabauer, Emily Theophilou, Cansu Koyuturk, Mona Yavari, Sathya Bursic, Alessia Telari, Alessia Testa, Raffaele Boiano, Davide Taibi, Davinia Hernandez-Leo, Udo Kruschwitz and Martin Ruskov. (03/2025). arXiv. https://arxiv.org/pdf/2503.02532
PAD: Personalized Alignment of LLMs at Decoding-Time

Ruizhe Chen, Xiaotian Zhang, Meng Luo, Wenhao Chai, Zuozhu Liu. (03/2025). arXiv. http://arxiv.org/pdf/2410.04070v6
MindCraft: Revolutionizing Education through AI-Powered Personalized Learning and Mentorship for Rural India

Arihant Bardia, Aayush Agrawal. (02/2025). arXiv. https://www.arxiv.org/abs/2502.05826
Co-designing Large Language Model Tools for Project-Based Learning with K-12 Educators

Prerna Ravi, John Masla, Gisella Kakoti, Grace C. Lin, Emma Anderson, Matt Taylor, Anastasia K. Ostrowski, Cynthia Breazeal, Eric Klopfer, Hal Abelson. (02/2025). arXiv. https://arxiv.org/pdf/2502.09799
EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces

Ghulam Mujtaba, Sunder Ali Khowaja, Kapal Dev. (02/2025). arXiv. https://arxiv.org/pdf/2503.00092
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

Jiamin Su, Yibo Yan, Fangteng Fu, Han Zhang, Jingheng Ye, Xiang Liu, Jiahao Huo, Huiyu Zhou, Xuming Hu. (02/2025). arXiv. https://arxiv.org/pdf/2502.11916
Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessments

Ryan A. Panela, Alexander J. Barnett, Morgan D. Barense, Bj‚àö‚àÇrn Herrmann. (02/2025). arXiv. https://arxiv.org/pdf/2502.13349
The Responsible Development of Automated Student Feedback with Generative AI

Euan D Lindsay, Mike Zhang, Aditya Johri, and Johannes Bjerva. (02/2025). arXiv. http://arxiv.org/pdf/2308.15334v3
SET-PAIRED: Designing for Parental Involvement in Learning with an Al-Assisted Educational Robot

Hui-Ru Ho, Nitigya Kargeti, Ziqi Liu, Bilge Mutlu. (02/2025). arXiv. https://arxiv.org/pdf/2502.17623
From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education

Yi-Fan Zhang, Hang Li, Dingjie Song, Lichao Sun, Tianlong Xu, Qingsong Wen. (02/2025). arXiv. https://arxiv.org/pdf/2502.13789
VTutor: An Open-Source SDK for Generative AI-Powered Animated Pedagogical Agents with Multi-Media Output

Eason Chen, Chenyu Lin, Xinyi Tang, Aprille Xi, Canwen Wang, Jionghao Lin, Kenneth R. Koedinger. (02/2025). arXiv. https://arxiv.org/pdf/2502.04103
SocratiQ: A Generative AI-Powered Learning Companion for Personalized Education and Broader Accessibility

Jason Jabbour, Kai Kleinbard, Olivia Miller, Robert Haussman, Vijay Janapa Reddi. (02/2025). arXiv. https://arxiv.org/pdf/2502.00341
Exploring the Potential of Large Language Models for Estimating the Reading Comprehension Question Difficulty

Yoshee Jain, John Hollander, Amber He, Sunny Tang, Liang Zhang, John Sabatini. (02/2025). arXiv. https://arxiv.org/pdf/2502.17785
The Art of Storytelling: Multi-Agent Generative AI for Dynamic Multimodal Narratives

Samee Arif, Taimoor Arif, Muhammad Saad Haroon, Aamina Jamal Khan, Agha Ali Raza, Awais Athar. (02/2025). arXiv. http://arxiv.org/pdf/2409.11261v4
The Imitation Game for Educational AI

Shashank Sonkar, Naiming Liu, Xinghe Chen, Richard G. Baraniuk. (02/2025). arXiv. https://arxiv.org/pdf/2502.15127
Scaffolding Middle-School Mathematics Curricula With Large Language Models

Rizwaan Malik, Dorna Abdi, Rose Wang, Dorottya Demszky. (02/2025). British Journal of Educational Technology. https://bera-journals.onlinelibrary.wiley.com/doi/10.1111/bjet.13571?af=R
One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction

Ben Liu, Jihai Zhang, Fangquan Lin, Xu Jia, Min Peng. (02/2025). arXiv.
Position: LLMs Can be Good Tutors in Foreign Language Education

Jingheng Ye, Shen Wang, Deqing Zhou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen. (02/2025). arXiv. https://arxiv.org/pdf/2502.05467
A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

Ziqing Li, Mutlu Cukurova, Sahan Bulathwela. (01/2025). arXiv. http://arxiv.org/pdf/2501.05220v1
Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models

Qiming Bao, Juho Leinonen, Alex Yuxuan Peng, Wanjun Zhong, Ga‚àö¬¥l Gendron, Tim Pistotti, Alice Huang, Paul Denny, Michael Witbrock, Jiamou Liu. (01/2025). arXiv. http://arxiv.org/pdf/2309.10444v5
A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT*

Yizhou Zhou, Mengqiao Zhang, Yuan-Hao Jiang, Xinyu Gao, Naijie Liu, Bo Jiang. (01/2025). arXiv. http://arxiv.org/pdf/2501.06819v1
Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources

Hannah-Beth Clark, Margaux Dowland, Laura Benton, Reka Budai, Ibrahim Kaan Keskin, Emma Searle, Matthew Gregory, Mark Hodierne, William Gayne, John Roberts. (01/2025). arXiv. https://arxiv.org/pdf/2502.10410
Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction

Yooseop Lee, Suin Kim, Yohan Jo. (01/2025). arXiv. https://arxiv.org/pdf/2501.13125
Generative AI in Education: From Foundational Insights to the Socratic Playground for Learning

Xiangen Hu, Sheng Xu, Richard Tong, & Art Graesser. (01/2025). arXiv. http://arxiv.org/pdf/2501.06682v1
IntelliChain: An Integrated Framework for Enhanced Socratic Method Dialogue with LLMs and Knowledge Graphs

Changyong Qi, Linzhao Jia, Yuang Wei, Yuan-Hao Jiang, Xiaoqing Gu. (01/2025). arXiv. https://arxiv.org/pdf/2502.00010
Leveraging AI for Rapid Generation of Physics Simulations in Education: Building Your Own Virtual Lab

Yossi Ben-Zion, Roi Einhorn Zarzecki, Joshua Glazer, Noah D. Finkelstein. (12/2024). arXiv. http://arxiv.org/pdf/2412.07482v1
ActiveAl: Enabling K-12 AI Literacy Education & Analytics at Scale

Ruiwei Xiao, Ying-Jui Tseng, Hanqi Li, Hsuan Nieu, Guanze Liao, John Stamper, Kenneth R. Koedinger. (12/2024). arXiv. https://arxiv.org/abs/2412.14200
Improving the Validity of Automatically Generated Feedback via Reinforcement Learning

Alexander Scarlatos, Digory Smith, Simon Woodhead, Andrew Lan. (12/2024). arXiv. http://arxiv.org/pdf/2403.01304v2
Generating Al Literacy MCQs: A Multi-Agent LLM Approach

Jiayi Wang, Ruiwei Xiao, Ying-Jui Tseng. (12/2024). arXiv. http://arxiv.org/pdf/2412.00970v1

Search and Filter

Submit a research study

Descriptive – Product Development

Takeaways

How Do Teachers Create Pedagogical Chatbots?: Current Practices and Challenges

Use Me Wisely: Al-Driven Assessment for LLM Prompting Skills Development

PAD: Personalized Alignment of LLMs at Decoding-Time

MindCraft: Revolutionizing Education through AI-Powered Personalized Learning and Mentorship for Rural India

Co-designing Large Language Model Tools for Project-Based Learning with K-12 Educators

EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models

Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessments

The Responsible Development of Automated Student Feedback with Generative AI

SET-PAIRED: Designing for Parental Involvement in Learning with an Al-Assisted Educational Robot

From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education

VTutor: An Open-Source SDK for Generative AI-Powered Animated Pedagogical Agents with Multi-Media Output

SocratiQ: A Generative AI-Powered Learning Companion for Personalized Education and Broader Accessibility

Exploring the Potential of Large Language Models for Estimating the Reading Comprehension Question Difficulty

The Art of Storytelling: Multi-Agent Generative AI for Dynamic Multimodal Narratives

The Imitation Game for Educational AI

Scaffolding Middle-School Mathematics Curricula With Large Language Models

One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instruction

Position: LLMs Can be Good Tutors in Foreign Language Education

A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

Exploring Iterative Enhancement for Improving Learnersourced Multiple-Choice Question Explanations with Large Language Models

A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT*

Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction

Generative AI in Education: From Foundational Insights to the Socratic Playground for Learning

IntelliChain: An Integrated Framework for Enhanced Socratic Method Dialogue with LLMs and Knowledge Graphs

Leveraging AI for Rapid Generation of Physics Simulations in Education: Building Your Own Virtual Lab

ActiveAl: Enabling K-12 AI Literacy Education & Analytics at Scale

Improving the Validity of Automatically Generated Feedback via Reinforcement Learning

Generating Al Literacy MCQs: A Multi-Agent LLM Approach