Breadcrumb
- Home
- AI Hub For Education
- Research Study Repository
- Descriptive – Product Development
Search and Filter
The Repository
Descriptive – Product Development
Research synthesis is AI-generated, human reviewed. Updated 11/2026.
Displaying 1 - 30 of 594
Calibrating LLM Tutor Initiation to Learner Expertise: Proactive and Reactive Support for Computational Thinking
Arun Rai, Liwei Chen, Balasubramaniam Ramesh, Cynthia Breazeal, Yuan Long, Benjamin M. Ampel, Andrea Aria. (11/2026). SSRN.
Overall, there was no average treatment effect on computational thinking across all 90 students.
Supporting Perspective Acquisition And Opinion Formation On Societal Issues Through AI-Generated Japanese Rap Battle Debates
Ryota Mibayashi, Toru Urakawa, Dai Takanashi, Tomoya Morohoshi, Kanata Yamagishi, Ryuho Sekikawa, Yasuhiko Nishimura, Yuta Takeuchi, Hideaki Tamori, Takehiro Yamamoto, Hidenari Kiyomitsu, Hiroaki Ohshima. (10/2026). arXiv.
Watching 1.5-minute rap battle debates nearly doubled the number of opinions and discussion points identified by participants, rising from 254 to 501 points.
Fairness Theatre: Evaluating Post-Hoc Fairness Interventions In Vendor-Controlled Early Warning Systems
Kelly McConvey, Angelina Zhai, Rebecca Li, Shion Guha. (09/2026). arXiv.
Post-hoc fairness interventions redistributed disparities without consistently reducing them, leaving error burdens for marginalized groups intact or worse while dashboard metrics appeared to improve.
Three Pathways Of Student-AI Interaction: Constraint-First Design For Higher-Order Thinking
Fatima Tuz Zahra. (09/2026). arXiv.
Undergraduate student interactions fell into three paths: 46% Passive Review, 18% Direct Question, and 36% Strategic Dialogue in primary classifications.
Argus: Academic Integrity In The Era Of Generative AI
David Racovan, Ajay Rawat, Christopher K. May, Jeffrey A. Turkstra. (09/2026). arXiv.
In Spring 2026, 45.7% of enrolled students were flagged for suspected LLM-assisted code development following automated triage and manual review.
Making The Invisible Visible: A Framework For Reflective AI Use In Software Engineering Education
Ali Shakiba, Thomas Chaffey. (09/2026). arXiv.
Retained students reported high perceived utility of AI assistance (mean 4.42/5) and high confidence in evaluating AI-generated outputs (mean 4.52/5).
A Benchmark For LLM'S Understanding Of Middle School And High School Science Topics
Noah L. Schroeder, Yessy Eka Ambarwati, Yuji Zhang, ChengXiang Zhai. (09/2026). arXiv.
Most tested models scored above 90% accuracy on middle and high school standards, with larger model size not consistently predicting higher performance.
Judgment-Centred Software Engineering Education: A Post-Hype Review And Framework For AI-Augmented Learning
Qusay H. Mahmoud. (09/2026). arXiv.
Generative AI can improve access to explanations and practice, but effects on assessed learning are highly uneven and depend on scaffolding, prior knowledge, and task design.
Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment For Non-Trivial Courses
Artur Jordao. (09/2026). arXiv.
More than 60% of surveyed students fully agreed that the automated grading exercises improved the integration of theory and practice.
"We'Ll Fix It Later": Education, AI, And The Deferral Of Privacy In EdTech
Meghna Manoj Nair, Rachel Greenstadt. (09/2026). arXiv.
One-third of audited platforms made no meaningful AI disclosure despite visible AI features, and 73% provided only generic accountability and breach-response language.
From Content Generation To Learning Support: Pedagogy-Guided Generative Video Tutors For STEM Learning
Xinchen Ma, Shuimu Wang, Gaole He, Yanbin Zhang, Chunyang Wang, Yunshi Lan, Weining Qian. (09/2026). arXiv.
The PIVOT framework generates educational videos with pedagogically aligned content, clear and engaging presentation, and coherent instructional flow across four STEM domains.
A Course Intelligence Platform For Higher Education: Lessons From AI-Assisted Course Evaluation
Bo Yuan, Jiazi Hu, Haimei Zhao. (09/2026). arXiv.
A domain-adapted model, Llama-UKP, achieved substantial agreement with expert judgments, reaching a Pearson correlation of 0.754 and a Spearman correlation of 0.843.
AI-Assisted Social Story Intervention For Special Education: The Design Of Adapted Stories
Buyankhishig Enkhjargal, Himanshi Lalwani, Hanan Salam. (09/2026). arXiv.
AI assistance suggests it can lower the burden of preparing Social Stories while supporting more individualized story creation.
Aware But Unprepared: Measuring The Security Awareness-Behavior Gap In Student Use Of LLM-Generated Code With Bifrost
Jaehwan Park, Seonhye Park, Kyungchan Lim, Doowon Kim, Doowon Kim. (09/2026). arXiv.
Over 95% of undergraduate students accepted insecure AI-generated code during programming tasks, despite 83.6% having completed security coursework.
Artificial Intelligence Driven Physics Assignments Using Context Prompts
Miguel Rodriguez, Peter Wulff. (09/2026). arXiv.
Context-prompted assignments helped students move beyond answer-seeking to connect introductory physics concepts directly to their jobs, hobbies, and everyday lives.
Reducing Barriers To Academic Support: Evaluating A Course-Specific RAG System For Addressing Help-Seeking Disparities In Higher Education
Andy Gray, Jake Hobbs. (09/2026). arXiv.
Most students agreed Beacon made private help-seeking easier (86.7%) and could benefit learners with low confidence (93.3%) or concerns about judgement (80%).
I Code Or AI Code: A Comparative Evaluation Of AI-Rated Scores In Classroom Observations
Yasmin Fong, Jane Xiang, Tak-Yue Dickson Chan, Kerry Lee, Eva Yi Hung Lau. (09/2026). arXiv.
AI and human ratings showed moderate agreement across CLASS dimensions (weighted kappa of 0.681), with AI scores typically falling within one scale point of human ratings.
An Evaluation Of AI-Supported Evidence-Based Learning For Public Speaking Skill Development
Sashini Hettiarachchi, Shahbaz Siddeeq, Mika Saari, Pekka Abrahamsson. (09/2026). arXiv.
All seven undergraduate participants improved their overall speech evaluation scores, with relative gains ranging from 6.5% to 120.0%.
Enhancing Procedural Writing Through Personalized Example Retrieval: A Case Study On Cooking Recipes
Paola Mejia-Domenzain, Jibril Frej, Seyed Parsa Neshaei, Luca Mouchel, Tanya Nazaretsky, Thiemo Wambsganss, Antoine Bosselut, Tanja Kaser. (09/2026). arXiv.
Participants receiving adaptive feedback improved their recipe writing quality and completeness significantly more than those without adaptive feedback.
Finding Common Mistakes In Modelling With Mathematical Formalisms Using LLMs
Lilian Killich, Marko Schmellenkamp, Fabian Vehlken, Thomas Zeume. (09/2026). arXiv.
On a propositional logic data set of 6,106 student pairs, the workflow discovered transformation clusters explaining 84.44% of student mistakes, including 15.03% not captured by previous hand-picked analyses.
Towards Scalable Measurement Of Durable Skills
Amir Globerson, Amy Keeling, Anisha Choudhury, Anna Iurchenko, Aviad Segal, Avinatan Hassidim, Ayça Çakmakli, Ben Gomes, Benn Witt, Cathy Cheunga, Cristine Legare, Diana Akrong, Eliad Carmi, Elisabeth Bauer, Gal Elidan, Hadas Gelbart, Hairong Mu, Katherine Chou, Lev Borovoi, Nir Kerem, Niv Efron, Noa Kerrem Gilo, Preeti Singh, Rajvi Kapadia, Rena Levitt, Roni Rabin, Ronit Levavi Morad, Rotem Yulzary, Shashank Agarwal, Sophie Allweis, Tracey Lee-Joe, Tzvika Stein, Yael Bar Moshe, Yael Haramaty, Yaniv Carmel, Yishay Mor, Yoav Bar Sinai, Yoav Bergner, Yossi Matias, Yuri Lev. (09/2026). arXiv.
Steering conversations with an Executive LLM significantly increased elicited evidence of collaboration skills compared to unconstrained AI teammates.
Tinker Tales: A Tangible Dialogue System For Child-AI Co-Creative Storytelling
Nayoung Choi, Jiseung Hong, Peace Cyebukayire, Ikseon Choi, Jinho D. Choi. (09/2026). arXiv.
Educationally scaffolded questions elicited narrative contributions in 90% to 100% of exchanges, compared to only 37% for general elaboration questions.
Generative AI And Extended Reality In Collaborative Architectural Design Education: An Exploratory Studio Study
Yao Xiao, Max Chen, Yichen Li, Nathaniel Powers, Maxwell Wiesenfeld, Gillian Smith, Soroush Farzin, Shichao Liu. (09/2026). arXiv.
Students using the GenARch pipeline experienced larger relative declines in design self-efficacy confidence and outcome expectancy, alongside a significant relative gain in perceived conflict management.
Ethics Training Agents: Facilitating Group-Based Ethics Education With Role-Playing And Discussion For Ethical Reflection And Exploration
Youngseok Seo, Sueun Jang, Hyesoo Park, Renz Samuel Gutierrez, Joseph Seering, Uichin Lee. (09/2026). arXiv.
Undergraduate STEM students showed statistically significant gains in both ethical issue awareness and ethical consequence reasoning after participating in the AI-facilitated discussions.
Embedded Human-Centered Data Science In A Graduate Programming Course: A Framework And Case Study
Victoria Chui, Kelly McConvey, Daniel Chui, Malayna Bernstein, Shion Guha. (09/2026). arXiv.
Overall survey scores improved significantly from pre-course to post-course (mean 72.3 to 75.8, p = 0.001), driven primarily by positive shifts in attitudes and perceptions toward ethical responsibility (p = 0.002).
An Emancipatory Vision For Designing (Generative) AI For Learner Flourishing
Luis Pablo Prieto, Yannis Dimitriadis. (09/2026). arXiv.
Current AI in education often relies on problematic assumptions, including treating agency as a zero-sum game, overestimating predictability in complex systems, and presuming infinite resources for permanent scaffolding.
Eduguard: A Safe RAG-Based LLM Tutor For Programming Education
S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha, Jungpil Shin. (09/2026). arXiv.
On the BILearn-CS benchmark, EduGuard achieved 90.1% correctness, 89.4% grounding, and reduced hallucination to 4.9% and direct-answer leakage to 9.8%.
AI-Augmented Inquiry And Regulation In Hybrid Systems: A Control Allocation Architecture For Preserving Epistemic Agency In Hybrid Human-AI Cognition
Jochen Kuhn, Peter Gerjets, Ulrich Trautwein, Jeffrey A. Greene, Sarah Malone, Patrik Vogt, Tim Fütterer. (09/2026). arXiv.
Hybrid cognition can become destabilized through seven interacting mechanisms, including control redistribution, germane effort attenuation, calibration drift, delegation drift, representational passivity, dual-threshold instability, and motivational-affective drift.
The 5P Reflection Model For Education In The Generative Artificial Intelligence (Genai) Era
Rajan Kadel, Samar Shailendra, Islam Mohammad Tahidul, Urvashi Rahul Saxena, Aakanksha Sharma, Sabitra Kaphle. (09/2026). arXiv.
Traditional reflection models fail to account for generative AI's probabilistic nature, risks of superficial synthesis, and the need to verify learner authenticity.
From Misconceptions To Evidence: What Science Teachers Make Visible When Co-Designing Agentic Learning Apps
Nizam Kadir, Wei Ting Liow, Sumbul Khan, Lay Kee Ang. (09/2026). arXiv.
All four design proposals focused AI on eliciting, scaffolding, or diagnosing scientific reasoning rather than generating answers.
