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 241 - 270 of 531 studies
Report From Workshop On Dialogue Alongside Artificial Intelligence
Thomas J. McKenna, Ingvill Rasmussen, Sten Ludvigsen, Avivit Arvatz, Christa Asterhan, Gaowei Chen, Julie Cohen, Michele Flammia, Dongkeun Han, Emma Hayward, Heather Hill, Yifat Kolikant, Helen Lehndorf, Kexin Li, Lindsay Clare Matsumura, Henrik Tjønn, Pengjin Wang, Rupert Wegerif. (11/2025). arXiv.
AI works most effectively as an augmentative mediating tool in human networks rather than as an autonomous replacement for human interaction.
Computational Blueprints: Generating Isomorphic Mathematics Problems With Large Language Models
Jeong-Hoon Kim, Jinwoo Nam, Geunsik Jo. (11/2025). arXiv.
During real-world deployment, CBIT-generated problems exhibited a user-reported content error rate of 0.1867%, which was 17.8% lower than expert-authored items.
Mentor: A Metacognition-Driven Self-Evolution Framework For Uncovering And Mitigating Implicit Risks In Llms On Domain Tasks
Liang Shan, Kaicheng Shen, Wen Wu, Zhenyu Ying, Chaochao Lu, Guangze Ye, Liang He. (11/2025). arXiv.
Across 14 language models, the framework reduced the average jailbreak success rate from 57.8% on raw responses to 4.4% after two revision rounds.
Understanding Student Interaction With Ai-Powered Next-Step Hints: Strategies And Challenges
Anastasiia Birillo, Aleksei Rostovskii, Yaroslav Golubev, Hieke Keuning. (11/2025). arXiv.
Across hint interactions, 28.48% were positive explicit acceptances, 40.00% were neutral, and 27.05% were negative, with most negative sessions caused by internal system errors.
Eduagentqg: A Multi-Agent Workflow Framework For Personalized Question Generation
Rui Jia, Min Zhang, Fengrui Liu, Bo Jiang, Kun Kuang, Zhongxiang Dai. (11/2025). arXiv.
EduAgentQG outperformed baseline approaches across diversity, objective consistency, and win rates, raising win rates by up to 4.75 percentage points with Gemini-2.5-Flash.
The Imperfect Learner: Incorporating Developmental Trajectories In Memory-Based Student Simulation
Zhengyuan Liu, Stella Xin Yin, Bryan Chen Zhengyu Tan, Roy Ka-Wei Lee, Guimei Liu, Dion Hoe-Lian Goh, Wenya Wang, Nancy F. Chen. (11/2025). arXiv.
Simulated students using SimLearner consistently performed within curriculum standards (77.2% to 91.6% knowledge coverage), whereas unconstrained baselines performed at 179.1% in grade 1.
AI Literacy For Community Colleges: Instructors' Perspectives On Scenario-Based And Interactive Approaches To Teaching AI
Aparna Maya Warrier, Arav Agarwal, Jaromir Savelka, Christopher A Bogart, Heather Burte. (11/2025). arXiv.
Instructors ranked interactive demonstrations highest among instructional support materials (mean rank 3.20 out of 4), followed by lecture slides, conceptual guides, and reflection prompts.
Autograder+: A Multi-Faceted Ai Framework For Rich Pedagogical Feedback In Programming Education
Vikrant Sahu, Raghav Borikar, Gagan Raj Gupta, Nitin Mane. (10/2025). arXiv.
Equipping a base model with dynamic prompt pooling achieved the highest alignment with teaching assistant feedback, reaching an average BERTScore F1 of 0.7658.
A Systematic Literature Review Of The Use Of Genai Assistants For Code Comprehension: Implications For Computing Education Research And Practice
Yunhan Qiao, Md Istiak Hossain Shihab, Christopher Hundhausen. (10/2025). arXiv.
Generative AI tools consistently improve code comprehension accuracy, task speed, and perceived usefulness, though benefits are larger for experienced professionals than students.
Evaluating Ai-Powered Learning Assistants In Engineering Higher Education: Student Engagement, Ethical Challenges, And Policy Implications
Ramteja Sajja, Yusuf Sermet, Brian Fodale, Ibrahim Demir. (10/2025). arXiv.
Most students found the AI tool more convenient (68%) and comfortable (47%) than asking human instructors, but only 17% rated its instructional quality as better.
"Learning Together": Ai-Mediated Support For Parental Involvement In Everyday Learning
Yao Li, Jingyi Xie, Ya-Fang Lin, He Zhang, Ge Wang, Gaojian Huang, Rui Yu, Si Chen. (10/2025). arXiv.
During the field deployment, 11 families completed 29 major tasks and 160 subtasks, with caregiver participation reaching up to 77% across evenly distributed tasks.
Multi-Stakeholder Alignment In Llm-Powered Collaborative Ai Systems: A Multi-Agent Framework For Intelligent Tutoring
Alexandre P Uchoa, Carlo ET Oliveira, Claudia L R Motta, Daniel Schneider. (10/2025). arXiv.
The Advisory Governance Layer architecture separates governance advisement from pedagogical logic across four specialized agent types, providing non-intrusive oversight without altering core tutoring decisions.
Directive, Metacognitive Or A Blend Of Both? A Comparison Of Ai-Generated Feedback Types On Student Engagement, Confidence, And Outcomes
Omar Alsaiari, Nilufar Baghaei, Jason M. Lodge, Omid Noroozi, Dragan Gašević, Marie Boden, Hassan Khosravi. (10/2025). arXiv.
Students receiving hybrid AI feedback were most likely to revise their work (27.5%), compared to 21.1% for directive and 12.1% for metacognitive feedback.
Designing Knowledge Tools: How Students Transition From Using To Creating Generative Ai In Steam Classroom
Qian Huang, Nachamma Sockalingam, Thijs Willems, King Wang Poon. (10/2025). arXiv.
Designing custom GPTs fostered student autonomy by allowing learners to decide the purpose, features, and content of their own AI tools.
Plural Voices, Single Agent: Towards Inclusive Ai In Multi-User Domestic Spaces
Joydeep Chandra*, Satyam Kumar Navneet*. (10/2025). arXiv.
The single-agent Agora-4B outperformed multi-agent baselines in compliance (76% versus 70%), fairness (90% versus 85%), and safety-violation rates (0% versus 7%).
Llmbridge: Reducing Costs To Access Llms In A Prompt-Centric Internet
Noah Martin, Abdullah Bin Faisal, Hiba Eltigani, Rukhshan Haroon, Swaminathan Lamelas, Fahad Dogar. (10/2025). arXiv.
In classroom deployments across three courses, student project inference costs were kept under $10 while handling roughly 500 requests per day.
Rubiscot: A Framework For Ai-Supported Academic Assessment
Thorsten Fröhlich, Tim Schlippe. (10/2025). arXiv.
Preliminary institutional testing showed promising improvements in thesis evaluation consistency and time efficiency.
Sketchmind: A Multi-Agent Cognitive Framework For Assessing Student-Drawn Scientific Sketches
Ehsan Latif, Zirak Khan, Xiaoming Zhai. (10/2025). arXiv.
Integrating Sketch Reasoning Graphs improved GPT-4o's sketch evaluation accuracy from 55.6% to 77.1%, while GPT-4.1 achieved the highest accuracy at 90.2%.
Tacla: An Llm-Based Multi-Agent Tool For Transactional Analysis Training In Education
Monika Zamojska, Jarosław A. Chudziak. (10/2025). arXiv.
Adult-to-Adult teacher responses de-escalated conflict with an average score of 3.733 out of 5, whereas Controlling Parent responses escalated conflict with a score of 2.167.
Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems In Math Competitions
Jialiang Sun, Yuzhi Tang, Ao Li, Chris J. Maddison, Kuldeep S. Meel. (10/2025). arXiv.
ECP formally solved 18 of 75 MathArena problems and 17 of 346 PutnamBench problems, outperforming baseline models under aligned budgets.
Farsimcqgen: A Persian Multiple-Choice Question Generation Framework
Mohammad Heydari Rad, Rezvan Afari, Saeedeh Momtazi. (10/2025). arXiv.
In human evaluation of 200 questions, 97.5% of questions and options were judged logically valid, and 94.5% of wrong choices were effectively distractive.
The Agency Gap: How Generative Ai Literacy Shapes Independent Writing After Ai Support
Yueqiao Jin, Kaixun Yang, Roberto Martinez-Maldonado, Dragan Gašević, Lixiang Yan. (10/2025). arXiv.
Proactive AI dialogues fostered stronger connections among conceptual reasoning, evidence use, and constructive engagement, whereas reactive interactions focused more on factual and procedural information.
Socratic Mind: Impact Of A Novel Genai-Powered Assessment Tool On Student Learning And Higher-Order Thinking
Jeonghyun Lee, Jui-Tse Hung, Meryem Yilmaz Soylu, Diana Popescu, Christopher Zhang Cui, Gayane Grigoryan, David A. Joyner, Stephen W Harmon. (10/2025). arXiv.
Engagement with the AI tool buffered against declining quiz performance, reducing the average drop in quiz scores by an estimated 3.30 points.
Personalized Learning Path Planing Through Goal-Driven Learner State Modeling
Joy Jia Yin Lim, Ye He, Jifan Yu, Xin Cong, Daniel Zhang-Li, Zhiyuan Liu, Huiqin Liu, Lei Hou, Juanzi Li, Bin Xu. (10/2025). arXiv.
Undergraduate students using the Pxplore platform improved mean test scores from 61.81% to 90.09%, achieving a 28.28% knowledge gain compared to 14.18% in the control group.
Learnlens: Llm-Enabled Personalised, Curriculum-Grounded Feedback With Educators In The Loop
Runcong Zhao, Artem Bobrov, Jiazheng Li, Cesare Aloisi, Yulan He. (10/2025). arXiv.
LearnLens achieved higher scoring accuracy and a correlation of 0.388 on 100 student answers, outperforming baseline models while cutting latency compared to QwQ-32B.
Ensembling Large Language Models To Characterize Affective Dynamics In Student-Ai Tutor Dialogues
Chenyu Zhang, Sharifa Alghowinem, Cynthia Breazeal. (10/2025). arXiv.
Students most frequently expressed neutral feelings (45.8%), confusion (22.15%), and curiosity (15.83%), while frustration (8.62%) and anxiety (0.41%) were comparatively rare.
Globalizeed: A Multimodal Translation System That Preserves Speaker Identity In Academic Lectures
Hoang-Son Vo, Karina Kolmogortseva, Ngumimi Karen Iyortsuun, Hong-Duyen Vo, Soo-Hyung Kim. (10/2025). arXiv.
Most students (77.7%) preferred dubbed formats over subtitled ones, reporting higher concentration (mean 4.06 out of 5) and reduced cognitive effort.
Evolution In Simulation: Ai-Agent School With Dual Memory For High-Fidelity Educational Dynamics
Sheng Jin, Haoming Wang, Zhiqi Gao, Yongbo Yang, Bao Chunjia, Chengliang Wang. (10/2025). arXiv.
The full model combining dual knowledge and experience memory with short- and long-term structures achieved the highest text similarity scores to expert ground truth.
Nim: Neuro-Symbolic Ideographic Metalanguage For Inclusive Communication
Prawaal Sharma, Poonam Goyal, Navneet Goyal, Vidisha Sharma. (10/2025). arXiv.
Semi-literate participants reached over 80 percent semantic comprehensibility by day five, outperforming benchmarked pictographic methods by 1.9 times in comprehensibility and 8.5 times in learnability.
Student-Ai Interaction In An Llm-Empowered Learning Environment: A Cluster Analysis Of Engagement Profiles
Zhanxin Hao, Jianxiao Jiang, Jifan Yu, Zhiyuan Liu, Yu Zhang. (10/2025). arXiv.
Cluster analysis identified two non-completer profiles (early dropouts and stagnating interactors) and three completer profiles (active questioners, responsive navigators, and lurkers).
