🏷️ formative-assessment

> **Synthesis:** Alsaiari et al. (2026) report a large-scale quasi-experimental cohort study (13,037 students; 51,296 student-authored resources) comparing three AI-mediated feedback workflows. Studen…

2026-08-13 · feedback-loop, learning-analytics, higher-ed, student-experience, self-regulated-learning

> **Synthesis:** Sperber et al. (2025) present the Peer and AI Review + Reflection (PAIRR) model, a human-centered approach to formative assessment that combines peer review best practices with AI rev…

2026-08-13 · ai-feedback-quality, writing-education, ai-literacy, student-experience, peer-review

> **Peer review** — the practice in which students read, evaluate, and provide feedback on one another's work, most often writing. In writing pedagogy, peer review is a long-standing best practice: st…

2026-08-13 · writing-education, ai-feedback-quality, student-experience, collaboration, self-regulated-learning

> **Synthesis:** Pecuchova, Benko, and Drlik (2026) investigate the capacity of a large language model (GPTo1) to generate formative feedback for student-created UML diagrams in a university software …

2026-08-10 · generative-ai, ai-feedback-quality, higher-ed, curriculum-design, self-regulated-learning

> **AI feedback quality** — the accuracy, usefulness, timeliness, and pedagogical value of feedback generated by AI systems for learners. As AI-generated feedback becomes ubiquitous in education, unde…

2026-08-09 · ai-feedback-quality, automated-grading, feedback-loop, generative-ai, ai-literacy

> **Assessment validity** — whether assessments measure what they claim to measure. AI in education raises fundamental validity questions: do AI-graded assessments assess student learning or AI prompt…

2026-08-09 · authentic-assessment, automated-grading, confidence-aware-ai-assessment, academic-integrity, rct

> **Automated assessment** — the use of AI to evaluate student work, from formative quizzes to high-stakes exams. Automated assessment spans multiple modalities — multiple-choice, short answer, essay,…

2026-08-09 · automated-grading, assessment-validity, bias-mitigation, teacher-role, automated-essay-scoring

> **Automated grading** — AI systems that evaluate student work, from multiple-choice scoring to essay assessment and code review. Automated grading is one of the most mature and widely-deployed AI in…

2026-08-09 · assessment-validity, automated-essay-scoring, ai-feedback-quality, bias-mitigation, confidence-aware-ai-assessment

> **Feedback loop** — the cyclical process where AI systems assess student work, deliver feedback, observe the student's response, and adapt subsequent instruction. Effective feedback loops close the …

2026-08-09 · ai-feedback-quality, automated-grading, scaffolding, self-regulated-learning, ai-tutoring

> **Learning analytics** — the measurement, collection, analysis, and reporting of data about learners and their contexts for the purpose of understanding and optimizing learning. AI has transformed l…

2026-08-09 · knowledge-tracing, student-modeling, privacy, edtech-platform, engagement-metrics

> Education AI is shifting from passive chatbots to **proactive agents** that initiate and pursue goals. This offers personalisation but risks undermining **learner agency and cognitive effort**. The …

2026-08-03 · agentic-ai, educational-theory, scaffolding, metacognition, human-in-the-loop

> Generative AI has not created the need for authentic assessment — it has made weaknesses in assessment design harder to ignore. Polished products can now be generated or substantially mediated by to…

2026-08-03 · authentic-assessment, assessment, assessment-validity, ai-ed-evaluation, generative-ai

> 1. **Evidence-Centered Design (ECD)** — assessments and rubrics aligned to curriculum goals from the start 2. **Human-in-the-loop prompt engineering** — labelled examples and prompts refined iterati…

2026-08-03 · automated-grading, human-in-the-loop, prompt-engineering, benchmark, ai-ed-evaluation

> **Responsible assessment in the AI era** — assessment grounded in learners' sociocultural contexts and designed to generate valid, trustworthy, context-specific inferences from accumulated evidence,…

2026-08-03 · assessment, assessment-validity, generative-ai, ai-ed-evaluation, educational-theory

Introduces ICLE++, a new annotated corpus of persuasive student essays that addresses critical limitations of the dominant ASAP benchmark in [[automated-essay-scoring]] research. Unlike ASAP — used by…

2026-07-31 · automated-essay-scoring, automated-grading, benchmark, educational-measurement, higher-ed

Survey of 206 engineering students: AI chatbots provide greatest perceived benefit as relief from competence frustration, smaller benefits for autonomy, weakest for relatedness. Baseline motivational …

2026-07-30 · higher-ed, stem-education, student-experience, affective-computing, personalized-learning

LLMs systematically underestimate the difficulty of misconception-driven items ('The Easy Trap'). While LLM ratings show moderate rank correlation with empirical student difficulty (rho=0.52-0.70), th…

2026-07-30 · llm, adaptive-learning, feedback-loop, student-experience, stem-education

Proposes Cognitive Diagnostic Profiling (CDP), a zero-shot framework that dramatically improves LLM-simulated examinee alignment with human test-takers. With CDP, IRT difficulty Spearman correlations …

2026-07-30 · llm, adaptive-learning, student-experience, benchmark, higher-ed

On 119,034 students across 13 UK national exams, Bernoulli Mixture Models found few distinct skill clusters — overall ability dominates. A simple explainable model achieved 78% accuracy, competitive w…

2026-07-30 · personalized-learning, stem-education, learning-analytics, student-experience, adaptive-learning

> **AICoFE** (AI-based Collaborative Feedback) is a multi-LLM feedback generation system for higher education that combines independently fine-tuned language models with **teacher-in-the-loop mediatio…

2026-07-29 · ai-ed-evaluation, feedback-loop, student-experience, human-in-the-loop-ai, higher-ed

This quasi-experimental mixed-methods longitudinal study (N=142) deploys a fully automated marking pipeline for handwritten mock examinations in A-Level sciences, removing the human-marking bottleneck…

2026-07-28 · assessment, automated-grading, k-12, stem-education, hybrid-e-assessment-semi-automated-grading

Generative AI undermines a basic premise of educational assessment: that submitted work reliably evidences the human capacities a credential certifies. This paper proposes *cognitive stewardship*, a f…

2026-07-23 · generative-ai, higher-ed, policy-maker, llm, assessment-validity

Tabletop exercises (TTXs) let learner teams rehearse high-stakes workplace tasks such as cybersecurity incident response, but their open-ended, collaborative nature makes [[formative-assessment]] diff…

2026-07-22 · feedback-loop, learning-analytics, stem-education, higher-ed, student-experience

This short paper provides rare descriptive classroom evidence on what happens when students repeatedly use generative-AI feedback across a full semester of writing coursework. Drawing on 2,988 reflect…

2026-07-20 · generative-ai, llm, higher-ed, writing-education, feedback-loop

This quasi-experimental study directly compares **AI-generated feedback** (two LLMs: **GPT-o4-mini** and **DeepSeek R1**) with **expert human-teacher feedback** in a project-based university course (A…

2026-07-19 · generative-ai, feedback-loop, higher-ed, student-experience, learning-gains

Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet most evaluations remain chart-centric and offer limited insight into **scientific visualization (SciVis)…

2026-07-17 · llm, generative-ai, stem-education, ai-literacy, benchmark

LEA (Learning Engagement Assistant) is an **agentic AI tutoring system** that couples course-specific retrieval-augmented generation (RAG) with structured [[knowledge-tracing]] / Knowledge Component (…

2026-07-16 · llm, generative-ai, intelligent-tutoring, higher-ed, stem-education

Introduces 'design problems' (DPs): concise, scenario-based prompts that require applying knowledge in transfer contexts, generated with LLMs to assess higher-order thinking (HOT) in project-based lea…

2026-07-14 · project-based-learning, generative-ai, stem-education, higher-ed, scaffolding

> Extends a prior validated protocol for classifying open-ended teaching-evaluation feedback by thematic category and sentiment, introducing a durability and cross-language transfer benchmark. Institu…

2026-07-14 · feedback-loop, automated-grading, teacher-role, higher-ed, faculty-development-genai

The widespread availability of general-purpose AI that can perform complex cognitive tasks threatens to undermine education at scale. This effortless bypass dilemma sharpens a challenge AIED has long …

2026-07-09 · over-reliance, student-experience, self-regulated-learning, metacognition, teacher-role

Debugging exercises are usually graded from final code and test outcomes, which hide *how* students reproduced failures, formed hypotheses, inspected evidence, edited code, and verified fixes. The aut…

2026-07-08 · programming-its, learning-analytics, cs-education, higher-ed, feedback-loop

Prompt engineering is a critical yet undertaught skill for software developers, poorly served by traditional instruction because of its evolving, interactive, context-dependent nature. The authors int…

2026-07-08 · agentic-ai, cs-education, feedback-loop, intelligent-tutoring, llm

As generative AI becomes central to software development, CS education is shifting toward prompt-centered workflows where students describe intended behavior in natural language to elicit code. But pr…

2026-07-07 · generative-ai, cs-education, over-reliance, metacognition, higher-ed

**Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J. Rodriguez-Martinez, Lorena Otero-Cerdeira (2026)** This paper presents an [[llm]]-based grading system for Linux/bash com…

2026-07-03 · llm, automated-grading, cs-education, higher-ed, scaffolding

**Mengqian Wu (2026)** Epistemic thinking — understanding how knowledge is constructed and justified — plays a central role in [[ai-literacy]], particularly when students co-program with generative AI…

2026-07-03 · ai-literacy, cs-education, student-ai-interaction, scaffolding, higher-ed

Data comics combine sequential visual narratives with data visualization to improve student engagement with [[generative-ai]] in educational settings. This paper evaluates the effectiveness of AI-assi…

2026-07-03 · ai-generated-content, k-12, active-learning, ai-literacy, llm

While [[llm]]s now enable rapid generation of learning materials like [[generative-ai]], evaluating the pedagogical quality of these materials remains an open challenge. This paper proposes an automat…

2026-07-03 · ai-generated-content, learning-analytics, higher-ed, llm, automated-grading

The rapid integration of [[llm]]s into [[intelligent-tutoring]] threatens to reduce mathematical learning to mere answer generation. This paper presents a design framework for AI tutors that act as re…

2026-07-03 · intelligent-tutoring, llm, scaffolding, higher-ed, automated-grading

> **Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J. Rodriguez-Martinez, Lorena Otero-Cerdeira** — Universidade de Vigo, submitted 30 Jun 2026…

2026-07-02 · llm, stem-education, scaffolding, higher-ed, llm-in-education

Hutchison et al. (2026) develop and validate a method for measuring critical engagement with AI code completion tools in educational settings. Using behavioral signals (time-to-accept, edit distance f…

2026-06-30 · higher-ed, llm, stem-education, student-experience

This paper explores how an embodied AI agent can act as a [[scaffolding|coach]] that accelerates human motor-skill development using [[adaptive-learning|reinforcement learning]]. The authors argue tha…

2026-06-25 · intelligent-tutoring, personalized-learning, scaffolding, adaptive-learning, professional-training

This study examines the [[student-modeling]] validity of **delayed start behavior** — when students begin assignments or practice sessions past a recommended start time — as a predictor of learning-ga…

2026-06-25 · learning-analytics, student-modeling, higher-ed, engagement-metrics, efficacy-study

Akgun and Toker (2026) examine whether learning gains from GenAI-enabled adaptive pretesting persist over a seven-week retention period. Undergraduate participants completed adaptive AI-assisted prete…

2026-06-23 · rct, adaptive-learning, learning-gains, higher-ed, personalized-learning

Imran and Bulathwela (2026) identify the 'correct answer trap' — automated feedback systems that judge only answer correctness reinforce rather than address misconceptions when students reach the righ…

2026-06-23 · llm, automated-grading, k-12, student-modeling

Tseng et al. (2026) investigate human-machine alignment in LLM-based pretest question evaluation — a critical bottleneck for scalable AI-assisted assessment. Their AI-assisted workflow combines automa…

2026-06-23 · ai-ed-evaluation, llm, teacher-role, assessment, automated-grading

Nagai et al. (2026) tackle the practical problem that many real-world educational datasets contain only single-time-point assessments (snapshots) without temporal information, making standard time-ser…

2026-06-23 · student-modeling, knowledge-tracing, adaptive-learning, learning-analytics, personalized-learning

> **Luyang Fang, Yingchuan Zhang, Jongchan Park, Zhaoji Wang, Ping Ma, Xiaoming Zhai** (2026). arXiv cs.AI preprint…

2026-06-19 · automated-grading, stem-education, k-12, efficacy-study, multi-representational-tools

> **Wei Xia, Jin Wu, Haoran Shi, Xiangyu Wang, Chanjin Zheng** (2026). East China Normal University / arXiv cs.CL preprint…

2026-06-19 · automated-grading, feedback-loop, writing-education, scaffolding, llm

AI-driven assessment of human tutor training performance correlates with real-life tutoring quality; bridges the gap between training metrics and classroom practice. AI-Driven Assessment of Human Tuto…

2026-06-18 · intelligent-tutoring, automated-grading, feedback-loop, teacher-role, efficacy-study

Evaluates cross-dataset generalization of ML/DL methods and LLMs for automatic Bloom's taxonomy classification of assessment questions across five datasets. Supervised ML/DL models degraded substantia…

2026-06-16 · automated-grading, llm, higher-ed, teacher-role, learning-analytics

**Misan Paul Etchie, Taiwo Olutosin** — cs.CY, cs.AI, cs.HC This paper proposes an AI-integrated LMS designed specifically for middle school instruction, addressing the gap between current LMS platfor…

2026-06-10 · k-12, adaptive-learning, personalized-learning, intelligent-tutoring, edtech-platform

**Hartwig Grabowski, Michael Canz** — cs.AI, cs.CV, cs.CY This paper identifies the didactic narrowing caused by fully digital e-assessment (overuse of closed question formats) and proposes a hybrid a…

2026-06-10 · automated-grading, assessment, higher-ed, generative-ai, llm

**Yibo Meng, Ruiqi Chen, Zhiming Liu, Xiaolan Ding** — Accepted at MobileHCI 2026 — cs.HC TibetCPR is a low-cost, self-guided CPR training system that pairs depth-driven electrotactile feedback with r…

2026-06-10 · professional-training, llm, student-experience, edtech-platform, higher-ed

Introduces **FOXGLOVE**, a dataset of 696 feedback comments by trained writing instructors on 69 twelfth-grade argumentative essays, paired with 1,644 comments from four frontier LLMs — totaling 2,340…

2026-06-09 · llm, writing-education, feedback-loop, higher-ed, k-12

Presents a **large-scale classroom study** (N=215 students, 6,693 submissions across 17 labs) deploying AI-generated feedback through a randomized protocol in an introductory Python programming course…

2026-06-09 · llm, feedback-loop, stem-education, higher-ed, automated-grading

Addresses a critical tension in [[stem-education|CS education]]: the widespread adoption of generative AI makes it impossible to distinguish authentic student effort from AI code synthesis by evaluati…

2026-06-09 · edtech-platform, academic-integrity, stem-education, higher-ed, scaffolding

This large-scale K-12 deployment provides empirical evidence that teacher-authored prompts can reliably shape the cognitive quality of student-AI dialogue at classroom scale. The TASD system lets teac…

2026-06-04 · k-12, student-ai-interaction, teacher-role, scaffolding, generative-ai

> **Authors:** Shim Jaechang, Unggi Lee (2026) — CIKM 2026…

2026-06-01 · intelligent-tutoring, llm, benchmark, efficacy-study, automated-grading

> **AI-ed evaluation** — the body of methods, benchmarks, and criteria used to assess whether AI education tools (LLM-based tutors, automated graders, feedback systems, agents) actually work — not jus…

2026-05-29 · llm, assessment, benchmark, teacher-role, generative-ai

**Catching the Correct Answer Trap** — accepted at AIED 2026 — exposes a critical blind spot in [[intelligent-tutoring]] systems: they systematically fail to detect misconceptions when students arrive…

2026-05-28 · intelligent-tutoring, automated-grading, llm, scaffolding, generative-ai

**Ethical AI Use in Higher Education: A Coordination Game Framework** provides a formal mechanism-level account of why policy statements alone fail to change student AI-use behavior. Reframing student…

2026-05-28 · higher-ed, academic-integrity, generative-ai, policy-maker, regulation

**LLM-Assisted Sentiment Analysis for Mixed-Methods Education Research** demonstrates how LLMs can serve as scalable qualitative research assistants, enabling researchers to investigate multiple demog…

2026-05-28 · llm, edtech-platform, higher-ed, learning-analytics, student-experience

**REC-CBM: Rubric-Aware Error-Correction Concept Bottleneck Models** advances the [[automated-grading]] frontier by solving a fundamental trust problem: even accurate AI graders are unusable if educat…

2026-05-28 · automated-grading, llm, higher-ed, scaffolding, efficacy-study

SlidesQAQA is a Flask-based system that extracts text and rendered images from PDF lecture slides and processes them through a four-stage [[llm]] pipeline: **window planning** (segment extraction), **…

2026-05-27 · prompt-engineering, generative-ai, llm, higher-ed, scaffolding

Automated grading systems have enabled scalable assessment for many response types, but handwritten mathematics remains a barrier due to the complexity of multi-step solutions. Vision-capable large la…

2026-05-22 · automated-grading, llm, stem-education, higher-ed, efficacy-study

Oral code reviews paired with a flipped classroom represent a pragmatic harm-reduction approach to generative AI in CS education. Rather than banning LLMs, Fowles et al. (2026) designed weekly formati…

2026-05-21 · generative-ai, higher-ed, cs-education, over-reliance, academic-integrity

🔗 [Code](https://github.com/adno/vocabulary-difficulty) This paper presents two complementary approaches to predicting vocabulary difficulty for language learners, achieving state-of-the-art results …

2026-05-20 · language-learning, llm, generative-ai, benchmark, scaffolding

RAG-based rubric-grounded GenAI writing feedback improved student revision quality (N=143, grades 7-11) and saved teacher time, but automated ratings were inconsistent. CyberScholar demonstrates rubri…

2026-05-19 · generative-ai, llm, writing-education, k-12, feedback-loop

This paper presents a systematic two-stage methodology for surfacing student misconceptions at scale. Drawing on 3,802 medical student enrollments across 5 biomedical science courses (9 course periods…

2026-05-16 · llm, generative-ai, higher-ed, learning-analytics, personalized-learning

KITE (Knowledge-Informed Tutoring Engine) introduces a [[intelligent-tutoring]] architecture that grounds its responses in course materials through a multimodal [[scaffolding|RAG pipeline]]. Unlike ge…

2026-05-16 · intelligent-tutoring, llm, generative-ai, scaffolding, higher-ed

> LaTA: A Drop-in, FERPA-Compliant Local-LLM Autograder for Upper-Division STEM Coursework **Rodríguez (2026)** — Oregon State University. Submitted to Computers & Education.…

2026-05-15 · automated-grading, higher-ed, stem-education, llm, generative-ai

**AI multimodal feedback matches educator feedback for learning while significantly outperforming it on student perceptions.** The authors built a real-time AI-facilitated multimodal feedback system i…

2026-05-11 · multimodal, feedback-loop, generative-ai, llm, student-experience

**Sequenced AI feedback harms learning despite boosting engagement and positive perceptions.** In a randomized experiment with 199 participants, the authors compared two types of AI-generated feedback…

2026-05-11 · feedback-loop, scaffolding, generative-ai, efficacy-study, student-experience

> A web-based system that uses LLMs and Learning Analytics dashboards to provide automated, rubric-based feedback on student presentation slides. Developed by Becerra et al. (2026), AISSA addresses th…

2026-05-09 · automated-grading, learning-analytics, higher-ed, llm, human-in-the-loop-ai

> An analysis of 310 AI-generated lesson plans (2,230 individual activities) produced by ChatGPT (GPT-4o), Gemini (1.5 Flash), and Copilot (GPT-4 based) for all 53 Massachusetts eighth-grade civics st…

2026-05-09 · k-12, ai-literacy, teacher-role, equity, pedagogical-llm-training

> A web-based writing environment that inverts the AI-tutoring paradigm: rather than generating improved text for students, Prober.ai constrains an LLM to ask only targeted inquiry-based questions abo…

2026-05-09 · writing-education, scaffolding, ai-literacy, higher-ed, metacognition

> **EduGage** (Leng et al., 2026) addresses a core challenge: in online/video-based learning, **learners must self-regulate** their engagement with instructional materials. > Sensor-based momentary as…

2026-05-08 · adaptive-learning, learning-analytics, affective-computing, higher-ed, feedback-loop

> **SCRIPT** (Deriyeva, Dannath, Paassen, 2026) implements an intelligent tutoring system for **Python programming** in a German university context, filling a gap in prior ITS which rarely supported P…

2026-05-08 · intelligent-tutoring, stem-education, higher-ed, adaptive-learning, student-misconceptions-conditionals-loops-taxonomy

> Schleifer, Ariely & Klebanov (2026) investigate a critical gap in [[automated-grading]]: **how scoring quality degrades for mid-range student responses**. Most ASAS evaluations focus on clearly corr…

2026-05-08 · automated-grading, llm, benchmark, efficacy-study, human-in-the-loop-ai

> While LLMs are increasingly used as teaching assistants, their teaching capability remains insufficiently evaluated — a critical gap in current AIED research. > Syllabus-grounded framework for measu…

2026-05-08 · llm, benchmark, personalized-learning, feedback-loop, ai-literacy

> Peer feedback develops critical reflection and evaluative judgment, yet: > Student peer feedback is often superficial or inconsistent. **AICoFe** (AI-based Collaborative Feedback) uses a multi-LLM p…

2026-05-07 · edtech-platform, feedback-loop, teacher-role, higher-ed, learning-analytics

> Wiggins (1990) proposed AA as a counterbalance to standardised tests: direct examination of "student performance on worthy intellectual tasks." > Authentic assessment (AA) has evolved from workplace…

2026-05-07 · ai-ed-evaluation, ai-education, assessment, higher-ed, metacognition

> Automatic Short Answer Grading (ASAG) is never perfect. Upper bounds on accuracy arise from: > Zero-shot LLMs perform strongly on ASAG without task-specific fine-tuning, but **model-based confidence…

2026-05-07 · automated-grading, llm, feedback-loop, higher-ed, learning-analytics

> ProPACT constructs a real-time model of pair collaboration using three signals: > Most adaptive learning systems are individual-centric and reactive. **ProPACT** treats **collaboration itself as the…

2026-05-07 · intelligent-tutoring, adaptive-learning, scaffolding, higher-ed, learning-analytics

> Benchmarking vision-language models (VLMs) not on their ability to solve problems, but on their ability to *support learners* — particularly struggling learners and those making errors. Traditional …

2026-05-07 · assessment, multimodal, benchmark, pedagogical-safety, stem-education

> Ostrowska, Kukla & Majstrak (2026) present an AI tutoring system **integrated into the Moodle LMS** designed to scaffold students from surface-level fact recall to deep conceptual understanding thro…

2026-05-07 · intelligent-tutoring, higher-ed, edtech-platform, llm, scaffolding

> Metacognition — thinking about one's own thinking — is both a target of AI education research (can AI tools develop students' metacognitive skills?) and a risk factor (AI completing tasks may suppre…

2026-05-07 · metacognition, self-regulated-learning, k-12, higher-ed, scaffolding

> Self-regulated learning (SRL) describes learners as active participants who can shape and develop their cognitive and behavioral actions in a successful way. AI tools can either scaffold SRL develop…

2026-05-07 · self-regulated-learning, metacognition, scaffolding, k-12, higher-ed

> Socratic dialogue — asking structured questions rather than providing answers — is one of the strongest pedagogical scaffolds for deep learning. When automated via AI, it produces measurable reasoni…

2026-05-07 · intelligent-tutoring, scaffolding, active-learning, higher-ed, stem-education