Breadcrumb
- Home
- AI Hub For Education
- Research Study Repository
- Evidence Explorer
- AI Tools
- Custom-built Research Tool
The Repository
Search and Filter
Custom-built research tool
Studies tagged with AI from their full text or abstract; see each study for details.
Showing 271 - 300 of 531 studies
Edumath: Generating Standards-Aligned Educational Math Word Problems
Bryan R. Christ, Penelope Molitz, Jonathan Kropko, Thomas Hartvigsen. (10/2025). arXiv.
The EDUMATH 30B model met all educational criteria on 94.6% of generated problems, outperforming closed models including GPT-4o, GPT-4.1, and GPT-4.5.
Expertagent: Enhancing Personalized Education Through Dynamic Planning And Retrieval-Augmented Long-Chain Reasoning
Binrong Zhu, Guiran Liu, Nina Jiang. (10/2025). arXiv.
Volunteer participants rated performance expectancy highest at 4.33 on a Likert scale, indicating the system could improve learning efficiency.
Ai In Computational Thinking Education In Higher Education: A Systematic Literature Review
Ebrahim Rahimi, Clara Maathuis. (10/2025). arXiv.
AI initiatives supported computational thinking education by personalizing instruction, addressing diverse student preparation, boosting motivation, and helping build core programming skills.
Uniedu: Toward Unified And Efficient Large Multimodal Models For Educational Tasks
Zhendong Chu, Jian Xie, Shen Wang, Zichao Wang, Qingsong Wen. (10/2025). arXiv.
UniEDU surpassed task-specific baselines in knowledge recommendation, time cost prediction, and answer prediction, gaining roughly 30% and 20% over top baselines on the first two.
Eduverse: A User-Defined Multi-Agent Simulation Space For Education Scenario
Yiping Ma, Shiyu Hu, Buyuan Zhu, Yipei Wang, Yaxuan Kang, Shiqing Liu, Kang Hao Cheong. (10/2025). arXiv.
Simulated teacher-student dialogue completion rates ranged from 0.28 to 0.64, closely matching real classroom rates of 0.37 to 0.49 across three text genres.
Harnessing Llm For Noise-Robust Cognitive Diagnosis In Web-Based Intelligent Education Systems
Guixian Zhang, Guan Yuan, Yanmei Zhang, Jing Ren, Ziqi Xu, Zhenyun Deng, Debo Cheng. (10/2025). arXiv.
DLLM consistently outperformed baseline cognitive diagnosis frameworks across all three datasets, achieving higher accuracy, AUC, and interpretability agreement scores.
Chrysalis: A Unified System For Comparing Active Teaching And Passive Learning With Ai Agents In Education
Prashanth Arun, Vinita Vader, Erya Xu, Brent McCready-Branch, Sarah Seabrook, Kyle Scholz, Ana Crisan, Igor Grossmann, Pascal Poupart. (10/2025). arXiv.
Students showed no significant overall preference or quiz score difference between learning from an AI tutor and teaching an AI agent.
Teachlm: Post-Training Llms For Education Using Authentic Learning Data
Janos Perczel, Jin Chow, Dorottya Demszky. (10/2025). arXiv.
Fine-tuning models on authentic tutoring data improved pedagogical performance, doubling student talk time and reducing tutor verbosity.
Ai-Driven Grading And Moderation For Collaborative Projects In Computer Science Education
Songmei Yu, Andrew Zagula. (10/2025). arXiv.
AI-generated grades showed high alignment with instructor-assigned grades, achieving a Pearson correlation coefficient of r = 0.91.
Human Empathy As Encoder: Ai-Assisted Depression Assessment In Special Education
Boning Zhao, Xinnuo Li, Yutong Hu. (10/2025). arXiv.
The multimodal framework achieved 82.05% accuracy and an 82.08% macro F1-score across 5-fold cross-validation when classifying seven depression severity levels.
Geolog-Ia: Sistema Conversacional Sobre Tesis AcadéMicas
Micaela Fuel Pozo, Andrea Guatumillo Saltos, Yeseña Tipan Llumiquinga, Kelly Lascano Aguirre, Marilyn Castillo Jara, Christian Mejía-Escobar. (10/2025). arXiv.
Geolog-IA achieved an average BLEU score of 0.87 when comparing its generated answers to actual database query results.
Editlens: Quantifying The Extent Of Ai Editing In Text
Katherine Thai, Bradley Emi, Elyas Masrour, Mohit Iyyer. (10/2025). arXiv.
EDITLENS achieved 94.0% accuracy in binary classification and 90.2% accuracy in ternary classification, outperforming existing detection baselines.
Lightweight Prompt Engineering For Cognitive Alignment In Educational Ai: A Oneclickquiz Case Study
Antoun Yaacoub, Jerome Da-Rugna, Zainab Assaghir. (10/2025). arXiv.
Detailed prompts with explicit level descriptions and action verbs achieved a 96% match rate to intended Bloom's levels, significantly outperforming simpler and persona-based prompts.
Code2Video: A Code-Centric Paradigm For Educational Video Generation
Yanzhe Chen, Kevin Qinghong Lin, Mike Zheng Shou. (10/2025). arXiv.
Code2Video achieved a 40% improvement in teaching effectiveness over direct code generation and substantially outperformed pixel-based video models.
Towards An Ai-Augmented Textbook
LearnLM Team. (09/2025). arXiv.
Students using the AI-augmented textbook scored significantly higher on both immediate (77% vs. 68%) and three-day retention assessments (78% vs. 67%) compared to digital reader users.
Future-Proofing Programmers: Optimal Knowledge Tracing for AI-Assisted Personalized Education
Yuchen Wang, Pei-Duo Yu, Chee Wei Tan. (09/2025). arXiv.
Students using the CoTutor system achieved the highest average assignment score (73.2%), outperforming baseline models and the traditional control group (68.4%).
ANVESHANAAI: A Multimodal Platform For Adaptive Ai/Ml Education Through Automated Question Generation And Interactive Assessment
Rakesh Thakur, Diksha Khandelwal, Shreya Tiwari. (09/2025). arXiv.
Fine-tuning Mistral-7B with 4-bit quantization achieved stable convergence, a low validation perplexity of 2.04, and a BERTScore F1 of 0.427.
From Frustration to Fun: An Adaptive Problem-Solving Puzzle Game Powered by Genetic Algorithm
Matthew McConnell, Richard Zhao. (09/2025). arXiv.
All three game versions moderately reduced puzzle-solving frustration, but differences among the models were not statistically significant.
DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces
Momin N. Siddiqui, Nikki Nasseri, Adam Coscia, Roy Pea, Hari Subramonyam. (09/2025). arXiv.
Readers using DraftMarks achieved 50% higher comprehension scores regarding the writing and revision process compared to a split-screen chat log baseline.
Student Engagement with GenAI's Tutoring Feedback: A Mixed Methods Study
Sven Jacobs, Jan Haas, Natalie Kiesler. (09/2025). arXiv.
Overall, 82.0% of AI feedback requests resulted in at least one code improvement, with students acting on 52.9% of the read feedback components.
AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
Yun Wang, Zhaojun Ding, Xuansheng Wu, Siyue Sun, Ninghao Liu, Xiaoming Zhai. (09/2025). arXiv.
AutoSCORE consistently improved scoring accuracy, human-machine agreement, and error metrics across most dataset-model combinations compared to single-agent baselines.
Leveraging Large Language Models for Robot-Assisted Learning of Morphological Structures in Preschool Children with Language Vulnerabilities
Stina Sundstedt, Mattias Wingren, Susanne Hagglund, Daniel Ventus. (09/2025). arXiv.
Tests showed the TalBot prototype successfully managed three-player turn-taking and used contextual cues to interpret children's mispronunciations or speech recognition errors.
Designing for Novice Debuggers: A Pilot Study on an Al-Assisted Debugging Tool
Oka Kurniawan, Erick Chandra, Christopher Michael POSKITT, Yannic Noller, Kenny Tsu Wei Choo, Cyrille Jegourel. (09/2025). arXiv.
Undergraduate participants gave the new tool an average System Usability Scale score of 75/100 and a satisfaction rating of 89/100, outperforming the previous version.
Experimentally Testing AI-Powered Content Transformations on Student Learning
Courtney Heldreth, Laura Vardoulakis, Nicole E. Miller, Yael Haramaty, Diana Akrong, Lidan Hackmon, Lior Belinsky. (09/2025). arXiv.
Students using Learn Your Way scored significantly higher on immediate recall (mean 9.2 out of 12) than those using a digital textbook (mean 8.2).
ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI
Ao Qu, Yuxi Wen, Jiayi Zhang, Yunge Wen, Yibo Zhao, Alok Prakash, Andres Salazar-Gomez, Paul Pu Liang, Jinhua Zhao. (09/2025). arXiv.
The AVA-Align video agent achieved 100% factuality and higher significance and feasibility scores than Gemini-2.5-Pro and Deep Video Discovery when evaluated on ten classroom videos.
Generative AI alone may not be enough: Evaluating AI Support for Learning Mathematical Proof
Eason Chen, Sophia Judicke, Kayla Beigh, Xinyi Tang, Zimo Xiao, Chuangji Li, Shizhuo Li, Reed Luttmer, Shreya Singh, Maria Yampolsky, Naman Parikh, Yi Zhao, Meiyi Chen, Scarlett Huang, Anishka Mohanty, Gregory Johnson, John Mackey, Jionghao Lin, Kenneth R. Koedinger. (09/2025). arXiv.
Students with access to LLM-Tutor scored significantly higher on homework assignments (99.64%) than the control group (96.55%), but exam performance and study time showed no significant differences.
OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning
Xian Gao, Zongyun Zhang, Ting Liu, Yuzhuo Fu. (09/2025). arXiv.
OnlineMate raised students' average cognitive level to 5.20 compared to 4.10 for standard multi-agent setups in simulations, while also boosting emotional engagement scores.
An Outcome-Based Educational Recommender System
Nursultan Askarbekuly, Timur Fayzrakhmanov, Sladjan Babarogic, Ivan Lukovic. (09/2025). arXiv.
An expert-curated fixed trajectory achieved the highest average learning mastery score (0.4641) despite lower user retention.
DeliverC: Teaching Pointers through GenAI-Powered Game-Based Learning
Wyatt Petula, Anushcka Joshi, Peggy Tu, Amrutha Somasundar, Suman Saha. (09/2025). arXiv.
Over 75% of surveyed students agreed that DeliverC supported confidence building, application, and metacognition, and 72% agreed it supported motivation.
Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
Xiaoming Zhai. (09/2025). arXiv.
Researchers use six major approaches to generate concept maps: human-in-the-loop, weakly supervised learning, domain-specific fine-tuning, prompt engineering, hybrid knowledge base integration, and modular frameworks.
