educational technology developers

Abstract: When students use generative AI to produce their work, the learning process becomes invisible. Established frameworks such as Bloom's taxonomy then classify the cognitive level of what the AI produced, not what the student contributed. We propose the Human Agency Depth Taxonomy (HADT), a preliminary six-tier taxonomy that classifies the engineering contribution a student makes in a prompt, independent of the AI's output. HADT combines three dimensions: contextual bandwidth, engineering abstraction and student agency. We applied HADT to 962 prompts from 105 students' structured AI Journals in an AI-permissive, first-year software engineering course of 145 students, and examined how agency changed over ten journalled weeks. Most prompts (84.2%) carried some student contribution beyond delegation. Agency tracked the development lifecycle. Architecture-discovery prompts dominated the requirements phase (48% of turns) and fell to 5-12% from week 9, while prompts analysing existing systems rose during build and verification (odds ratio 2.88, with turns clustered by student). Two-thirds of the variance in tier lay within students, so agency depended more on the phase of work than on the student. A turn-level rise in delegation in deadline weeks did not hold once turns were clustered by student. Explicitly specifying constraints on the AI's output was rare throughout, which we interpret as a knowledge bottleneck for novices rather than a gap in instruction. We discuss implications for course and assessment design, and for using HADT as a formative lens on how students engage with AI.

Abstract: As agentic AI in education shifts from reactive tools toward partners that take initiative and persist over time, a central question is how learners relate to, evaluate, and benefit from artificial agency. We conducted a longitudinal experiment in an undergraduate learning analytics course, in which 17 student teams (N = 48) collaborated with a persistent LLM-based teammate across weekly sessions. The agent decided when to intervene through a trigger-based architecture, and its social role was manipulated between teams: a Cognitive Agent that challenged quick consensus or a Supportive Agent that invited quieter members to contribute. Combining chat discourse, post-session surveys, and spoken reflections, we identified distinct patterns unfolding across three timescales. Students accommodated their language to the agent's role immediately, using more social language toward the Supportive Agent from the first session. Their helpfulness evaluations were recalibrated from session to session in relation to the agent's observed behavior, rather than remaining anchored to students' pre-existing attitudes toward AI. A slower crossover emerged in perceived collaboration process and positive-affect word use in reflections: Supportive-Agent teams began below Cognitive-Agent teams and ended above them, although students rated the Supportive Agent less helpful throughout. Because these responses follow different trajectories, single-session evaluations of agentic AI may miss changes that emerge only through repeated interaction.

Abstract: Artificial intelligence (AI) agents are increasingly explored as collaborative learning partners in mathematics education, yet it remains unclear what makes an AI recognizable as a peer. This study examines how domain experts perceive and interact with an adaptive LLM-based peer agent combining a Big Five-informed persona with motivational state modulation for collaborative mathematics problem solving. Through thematic analysis of expert interviews, we identify conditions shaping peer perceptions, including emotional safety, shared control, and collaborative reasoning. Participants primarily judged the AI through its social behavior rather than mathematical capabilities. The AI was perceived more as a peer when it created a non-judgmental space, engaged in tentative reasoning, displayed appropriate imperfection, and respected participants' pace. Conversely, blind agreement and over-instruction reduced trust and shifted perceptions toward a tutor role. Based on these findings, we propose human-centered design dimensions for AI peer agents to guide future peer-oriented learning systems.

Abstract: Large language models (LLMs) are increasingly used for learning, raising a key question: can learners remain epistemically proactive, retaining responsibility for the cognitive and regulatory activities through which learning is produced while working with AI? Because this responsibility may change as interactions unfold, we examine epistemic proactivity as a developing process. We conceptualize epistemic proactivity through self-regulated learning (SRL) moves, complemented by help-seeking strategies and manifestations of epistemic vigilance. We analyzed these behaviors in 880 substantive turns from 112 secondary-school students completing open-ended mathematical-modeling practice with a general-purpose LLM (Mistral). Overall, students showed limited observable epistemic proactivity: their interactions were strongly request-dominated, with planning, monitoring, and evaluation relatively rare, although low-quality AI responses elicited more explicit evaluation. Temporal analyses qualified this picture: explicit SRL-related moves increased modestly over the chat, but help-seeking strategies became less understanding-oriented. Crucially, these temporal trajectories in help-seeking strategies predicted their post-test performance without AI beyond pre-test and aggregate patterns: students whose requests became more understanding-oriented performed better once AI assistance was removed. Thus, while students had a limited epistemic proactivity overall, its temporal development still was a critical predictor of post-test performance without AI. These results underscore the importance of examining the temporal organization of epistemic proactivity, rather than isolated prompt types, for understanding AI-supported learning. We release our fully-anonymized dataset publicly in an OSF repository.

Abstract: Whether generative AI (GenAI) use helps or hinders critical thinking remains contested, and existing accounts emphasize exposure to the tool rather than how a person structures their engagement with it. Extending Transactive Memory Systems (TMS) theory to human-AI partnerships, we test a structural account of critical thinking in GenAI-assisted academic work among 891 college students in the United States and Türkiye. Self-appraised thinking ability and confidence in the partnership shaped how much practical experience a person built up with GenAI, but neither predicted critical thinking directly. That experience mattered only through two downstream behaviors, dividing and coordinating cognitive labor with the tool, and actively reworking its output rather than accepting it as given. A multigroup comparison found this structure largely invariant, with two theoretically interpretable exceptions. This study offers a structural, TMS-based account of critical thinking in GenAI-assisted work.

Abstract: In formal systems such as Lean 4, efficiently finding answers to mathematical problems and generating verifiable proofs is an important task in automated mathematical reasoning. In the traditional way where an upstream solver provides multiple candidate answers, the common workflow requires searching for proofs for each candidate separately, incurring redundant computational cost. To this end, we propose a joint proof framework that integrates candidate answer selection, answer supplementation, and formal proof generation into a unified reasoning process. At its core is a trained prover that selects given or proposes new answers and generates a proof for at least one answer in a single call. Joint proof can also reuse generated proofs to check for faithfulness errors. For problems with a unique answer, if two distinct answers both obtain verifiable proofs under the same formal statement, this confirms the statement does not faithfully preserve the original problem semantics. On MATH-500, AMC 2023, and AIME 2024/2025/2026, our framework achieves the same formal proof success rate as per-candidate proof generation with about one sixth of the token cost, and identifies at least 6.1% of the formalized statements as unfaithful without requiring additional judges. Our model and code are available at https://github.com/Linppz/Gobble-Prover.

Abstract: We studied 153 students in an undergraduate proof-based mathematics course with staggered-access to an AI support system. Students were randomly assigned to receive an AI chatbot and a homework-feedback interface earlier or later in the course. During the period when only the early-access group had access, their homework scores were 2.56 points higher, but exam performance did not differ significantly between groups, suggesting that improved AI-supported homework performance did not translate into detectable gains on a subsequent exam. After all students received access, every additional 100 messages sent to the AI chatbot was associated with a 3.02-point lower score on the subsequent exam. A mediation analysis showed a significant indirect association linking lower baseline self-efficacy to greater chatbot use and, in turn, lower exam scores: a one-point decrease in self-efficacy corresponded to 0.62 fewer exam points through chatbot use. These findings raise concerns that students may use the chatbot to offload their cognitive reasoning. Use of the homework-feedback interface, which required students to submit their proof attempts before receiving feedback, was not negatively associated with exam performance. We recommend against using a chatbot for AI tutoring and suggest exploring a tutor embedded in the course activities.

Abstract: Understanding a one-to-one tutoring video requires more than recognizing its events. A model must connect a visible teacher intervention to the learner response it elicits and to the follow-up adjusted to that response. Existing video and educational-dialogue benchmarks typically emphasize event recognition, temporal reasoning, social-state inference, or transcript-based interaction, but rarely diagnose this action-response-adjustment relation. We introduce VIRA-Bench, a focused diagnostic benchmark for short-horizon pedagogical contingency in one-to-one online tutoring. VIRA-Bench contains 1,005 tutoring clips and 1,322 multiple-choice questions with researcher evidence audit and expert verification, organized into Observable Evidence Grounding (OEG), Interaction Contingency Reasoning (ICR), and Support-Response Modeling (SRM). Across 11 models, the best reaches 61.3%, well below the 91.0% human reference on a stratified subset, and ICR generally has the lowest layer accuracy among leading models. Under controlled input manipulations, removing video most strongly degrades OEG, whereas disrupting temporal order most strongly degrades ICR. Free-response, Stem+Options, and synchronized-shuffle controls show that response format, static question cues, and video-ASR mismatch do not explain these layer-specific patterns. The results identify distinct behavioral evidence dependencies without claiming an internal architectural mechanism. VIRA-Bench provides a focused evaluation resource for multimodal dialogue grounding, pedagogical discourse, and temporal reasoning in online tutoring.

Abstract: Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often holds at the aggregate level, we present systematic evidence that vision-language models (VLMs) exhibit inverse scaling at the subtask level: specific question categories on which larger models perform worse than smaller counterparts within the same model family. We evaluate 19 models from four distinct model families across eight multimodal benchmarks (nine evaluation splits), answering 29,386 questions per model, 558,334 model-question evaluations in total. Using per-question pairwise analysis across all model pairs in each family, we identify 375 subtask-model-pair combinations exhibiting inverse scaling, spanning 4,342 unique queries where a smaller model answers correctly but a larger model fails, and we find that these patterns replicate across independently developed architectures. We identify 13 subtask-dataset pairs that show inverse scaling across multiple families, consistent with the phenomenon being task-driven rather than model-specific. The most affected domains in our study include multi-image spatial reasoning, visual perception, and university-level STEM knowledge, with accuracy gaps exceeding 20 percentage points in several cases, while diagram understanding appears comparatively resistant. These findings challenge the assumption that increasing model size uniformly improves multimodal capabilities and suggest that model selection should be task-aware.

Abstract: Indonesia's fragmented geography and uneven infrastructure pose persistent challenges for adopting new educational technologies. While national initiatives aim to mainstream AI in K-12 schools by 2025, policy readiness does not automatically mean teachers are ready for the classroom. This study surveys Indonesian K-12 teachers to examine: (1) their understanding of AI, (2) how they and their students use AI, and (3) their views on the acceptability of AI in learning activities. Through semi-automated thematic analysis, we identify common misconceptions and use cases. Our findings reveal a notable mismatch: while teachers find AI use in education acceptable and support it for the sake of efficiency, they remain fully aware of the risks to learning depth and academic honesty. We also find that this high level of acceptance is currently coupled with a poor understanding of how AI actually works.

Abstract: What a newborn sees, hears and feels, and how this changes month by month, has been measured sense by sense, with different methods and in different units. We bring these measurements together for the first two years of life and ask whether small neural networks tuned to a given age can turn them into a quick, inspectable simulation of sensory perception. Each sense's immaturity is written as a fixed, age-indexed filter on the input, and a small prediction network learns behind it over the first year. The filters alone reproduce the order in which the senses mature, by construction. The networks add what filters cannot: in vision they extract far less than their input allows at early stages (at the newborn stage a toy's position cannot be read out, $R^2 = 0.00$, against 0.57 for a network trained directly on the same input), and a critical period and perceptual narrowing emerge without being built in; in hearing they track what their input allows. The same filters drive the Baby Senses Lab, a free website that shows a user's own images and sounds as a baby of a chosen age might sense them. It is a research and teaching tool, not a diagnostic test.

Abstract: Teachers increasingly configure educational chatbots through natural-language instructions, but how these bots fail in real-world use remains poorly understood. We introduce EduWild, a dataset of 1,726 conversations with 217 teacher-configured chatbots, each paired with the instructions and configuration behind it, including 900 conversations from the intended end users of 35 deployed chatbots. We develop a 29-code taxonomy covering factual, workflow, diagnostic, and pedagogical failures and apply it using a human-calibrated LLM judge. The most frequent failures are lapses in following teacher intent --- bots skip required workflow steps (53.8% of end-user conversations), omit expectation setup (33.4%), and overload learners with information or questions (37.1%). Guided by these findings, we design a prompt-based harness targeting the six most frequent failure modes. In a study with 200 college students across ten bots, the harness reduces the mean number of target failure codes per conversation from 1.406 to 0.489, a 65.2% relative reduction with bots weighted equally. These findings show how real-world failure analysis can guide practical improvements to educational chatbots.

Abstract: Generative artificial intelligence (GenAI) models, particularly large language models (LLMs), are increasingly used in educational settings for tasks such as item generation, automated scoring, and feedback delivery. The quality of these outputs depends not only on the AI model but also on how users construct the prompts that guide model behaviors. Current prompt engineering practices are largely ad hoc, relying on trial and error rather than principled design. This lack of structure introduces validity threats including construct misrepresentation, construct-irrelevant variance, and limited reproducibility. We propose that Evidence-Centered Design (ECD), a framework in educational measurement for structuring valid inferences from observed performance, can serve as a principled foundation for prompt engineering in educational applications. We map the three core ECD models, the student model, the evidence model, and the task model, onto the components of educational prompt design, and describe a workflow for ECD-based prompt engineering. We derive five design principles from this mapping and present an empirical study contrasting ECD-designed prompts with state-of-the-art (SOTA) prompting baselines on an automated scoring task. Our empirical study demonstrates the usefulness of this framework on automated scoring. Results suggest that treating prompting as assessment design rather than informal instructions strengthens the validity, reliability, and fairness of AI-generated educational outputs.

Abstract: As Large Language Models (LLMs) are increasingly adopted for automated grading and feedback in higher education, their structured outputs, including multi-dimensional rubric scores, detailed feedback comments, and improvement suggestions, create an appearance of thorough analytic evaluation. This study examines whether these outputs deliver what they appear to offer. Using the JorGPT dataset of 3,041 student responses to 50 open-ended computer science questions, scored by both human instructors and three commercial LLMs, we identify three systematic discrepancies between the apparent and actual quality of LLM-generated grading and feedback. The sub-dimension scores are highly correlated (r = 0.82-0.99, VIF up to 45), providing redundant rather than independent diagnostic information. The textual feedback rarely detects student misconceptions (5-7% vs. 15-31% for teachers), functioning as a coverage checklist rather than a diagnostic instrument. The feedback tone remains uniformly positive regardless of response quality, lacking the severity modulation observed in human feedback. Additionally, grading accuracy varies significantly by knowledge domain, with procedural topics most reliable. These findings provide empirically grounded guidance on which aspects of LLM-generated grading and feedback can be relied upon and which require continued human oversight.

Abstract: Large language models (LLMs) trained to answer questions are natively poor at teaching. Reinforcement Learning (RL) against a simulated student is a promising approach to improve their pedagogy, but existing RL-trained tutors reward the student's success on the tutored problem with the tutor's words still in context. The reward is then easiest to raise by telling the student the answer, and a tuned penalty is needed to reduce telling. Drawing on learning sciences, we introduce a masked near-transfer post-test: the student is tested on an unseen variant of the tutored problem with the tutor's utterances masked, so the reward can rise only through what the student wrote in its own turns. This discourages cognitive offloading by the student and allows the continuous penalty to be replaced by two binary reward gates (factual correctness of tutor response, no solution handover). A leave-one-out ablation shows that the learning-gain reward on its own does not separate teaching from telling: the gates reduce solution handover while the near-transfer post-test improves out-of-domain transfer. Using these reward designs we develop Eduardo, a multi-turn RL recipe for training LLM tutors, and use it to train 4B, 9B, 14B and 27B models from two distinct LLM architectures. Our post-trained Eduardo-27B model matches Gemini-3.1-Pro on MathTutorBench and Claude Opus 4.8 on TutorMoments at 2.4-6.2x fewer thinking tokens than frontier models, which matters for interactive tutoring. Without being named in the reward, the model more than doubles its use of the push-for-justification teacher move while support fading (e.g., assigning independent work), whose payoff lies beyond a single-problem dialog episode, is trained out. We open-source our training environment, an 8,671-problem near-transfer dataset, and trained models for further development.

Abstract: Academic dishonesty is an urgent problem in computer science (CS) education, compounded by the rise of artificial intelligence (AI) and the prevalence of online learning in a post-COVID world. Self-efficacy and the impostor phenomenon are psychological constructs linked to academic dishonesty, yet little research has examined how they relate to how students perceive it. This study investigates the interplay between the impostor phenomenon, self-efficacy, and CS students' perceptions of academic integrity, in a context where online learning and AI agents have become commonplace. We conducted an online, asynchronous survey of undergraduate students (n = 443) in introductory to mid-level computing courses at a large Southeastern U.S. university. The survey collected measures of self-efficacy, responses to 13 potential cheating scenarios, the impostor phenomenon (Clance Impostor Phenomenon Scale), and demographic information. We observed a significant negative correlation between self-efficacy and the impostor phenomenon, and a positive correlation between the impostor phenomenon and judging an AI-related scenario as serious cheating. The impostor phenomenon was also correlated with perceived course dedication and prior teaching assistant (TA) experience, whereas self-efficacy was correlated with ethnicity. These findings highlight the need to better understand students' perceptions of AI and to keep the impostor phenomenon present in conversations about academic integrity in higher education scenarios.

Abstract: Generative artificial intelligence (GenAI) is increasingly embedded in university students' academic work, yet student engagement is often examined through adoption, frequency of use, or general perceptions, with less attention to how it is shaped by linguistic and sociotechnical conditions. This comparative qualitative study examines how university students access, incorporate, and evaluate GenAI across three contrasting higher education settings in China, Japan, and Mongolia. Semi-structured interviews were conducted with 42 undergraduates from one university in each setting, and the data were analyzed through qualitative interpretation supported by co-occurrence network and correspondence analyses using KH Coder. Across the three samples, GenAI was incorporated into academic practices spanning exploration, production, and refinement. However, access pathways differed across the three contexts. Participants in China navigated between domestic and global GenAIs, those in Japan predominantly used global GenAIs through Japanese, and those in Mongolia more frequently shifted to English when Mongolian outputs were perceived as less satisfactory. During their use of GenAI, students evaluated its accuracy, privacy implications, potential for dependence, and effects on critical thinking. The findings suggest that technological access alone does not ensure equivalent educational usability across linguistic and sociotechnical contexts. Building on the empirical findings and the analytical perspectives, an empirically informed integrative framework is developed in which student GenAI engagement is understood as situated, mediated, enacted, and evaluated. The framework conceptualizes realized affordances as educational possibilities that become practically usable through the interplay of sociotechnical conditions, linguistic resources, academic practices, and evaluative judgments.

Abstract: Effective adaptive instructional systems require robust measures of learner engagement that go beyond static user profiles. This study employs Multimodal Learning Analytics (MMLA) to investigate the relationship between self-reported instructional modality preferences and objective neurophysiological markers of engagement. Thirty-seven participants engaged with learning content delivered via varying modalities (visual, auditory, reading/writing, kinesthetic). We captured real-time neural activity using two EEG devices: the Emotiv EpocX (14 channels, 128 Hz) and OpenBCI (16 channels, 125 Hz). Preferences were assessed using the VARK questionnaire. Consistent with literature challenging the "meshing hypothesis," aligning instructional modality with stated preferences did not significantly predict performance gains. However, spectral analysis of EEG data revealed divergent engagement patterns: when content aligned with preferences, distinct neural activity patterns emerged in theta and alpha frequency bands-markers associated with attention and cognitive processing. These signals were used to train a binary logistic regression classifier, achieving a mean accuracy of 83.21% with OpenBCI and 56.27% with Emotiv EpocX. These findings suggest that while self-reported preferences may not dictate learning outcomes, they significantly influence neurophysiological engagement, offering a viable, non-invasive input for adaptive educational algorithms.

Abstract: A generative AI teaching partner should support reasoning over supplying conclusions; however, this has not been tested against learning in an authentic course. Drawing on design-based research, we specify the position as a conjecture map and report a first design cycle in two graduate-level research methods courses. Students used an AI teaching partner employing a constraint-first sequence requiring them to state and justify positions before receiving questions. Pre- and post-measures of AI literacy, critical thinking, and metacognitive awareness were collected alongside interaction records. AI literacy increased, concentrating in understanding AI, whereas critical thinking, awareness, and knowledge did not change. Since changes were limited to self-report measures, they may reflect growth in confidence instead of capacity. Interaction records, meanwhile, showed brief exchanges, uneven enactment of the constraint-first sequence, and missing records. These findings show why AI-supported learning requires interaction records to provide a more defensible basis for AI-supported designs than self-reports.

Abstract: On-policy distillation (OPD) trains a student on its own reasoning trajectories using feedback from a stronger teacher. Teacher interventions can improve these trajectories, but also change the distribution on which the student learns. Our controlled studies show that rollout quality alone is an incomplete criterion for allocating teacher guidance. Deeper intervention yields diminishing gains in rollout accuracy while increasing off-policy load. In a training probe with a restricted rollout horizon, peak student accuracy and performance retention favor different intervention strengths. The preferred intervention depth and placement also vary across benchmarks. These findings motivate MAESTRO, which uses local policy disagreement to jointly adapt when the teacher takes over and how long it generates. Its {policy disagreement score} combines teacher-weighted candidate coverage with local distribution similarity and is aggregated within reasoning paragraphs. Across eight mathematical reasoning benchmarks, MAESTRO achieves the highest macro-average accuracy among the compared methods for both 0.6B and 1.7B Qwen3 students, with the 1.7B student leading on every benchmark. MAESTRO also reduces average training response length by 67.3\% relative to standard OPD. The code is available at https://github.com/yhao-wang/MAESTRO.

Abstract: A key challenge in physics diagram understanding is correctly associating visual information with the physical entities, relations, and conditions it describes. Even when a value, symbol, or other local element is accurately recognized, assigning it to the wrong entity or scope can distort the underlying physical premise and lead to incorrect reasoning. To systematically study this challenge, we introduce \textbf{PhysAlign}, a benchmark designed to assess whether multimodal models correctly associate information recognized from physics diagrams with its intended physical role. By disentangling visual recognition from physical-role assignment through localized probes and controlled variants, PhysAlign isolates correspondence errors from recognition failures. It contains 3,341 human-validated probes spanning 986 physics problems, enabling systematic evaluation of visual recognition and physical-role correspondence at scale. We further introduce five complementary evaluation metrics, including CAcc, GAcc, and JAcc, which provide a comprehensive assessment of models' ability to recognize diagram content, establish correct physical correspondences, and solve the underlying physics problem. Across our evaluated multimodal models, PhysAlign reveals a consistent gap between local visual recognition and physical-role grounding. Even when the queried content is correctly recognized, the conditional correspondence error rate remains 13.8\% for GPT-6-Astra and rises to about 50.6\% for InternVL3.5-8B. These findings indicate that strong perception alone does not ensure reliable physical interpretation, exposing a distinct grounding bottleneck that is largely hidden by answer-level accuracy and highlighting the need for future models to better align recognized visual evidence with its physical meaning.

Abstract: Current Large Language Models (LLMs) excel at solving complex mathematical problems, yet this proficiency does not inherently translate into effective tutoring. While advanced LLM tutors may leverage multi-agent frameworks or fine-tuning, most still lack a mechanism to systematically accumulate and reuse pedagogical experience over time, limiting their adaptability to diverse student needs during fluid, multi-turn interactions. To bridge this gap, we propose the Reflective Experience-Augmented Tutoring (REAT) framework, which couples experience distillation from historical dialogues with real-time adaptive retrieval. Driven by a multi-agent Observer-Critic-Mentor (OCM) distillation pipeline, REAT reviews past conversational trajectories and distills raw interactions into structured, problem-agnostic pedagogical experiences. During live tutoring, a state-aware retrieval module injects these curated experiences to provide adaptive scaffolding based on the student's cognitive state. Experiments demonstrate that the proposed framework significantly outperforms both prompt-only and supervised fine-tuning (SFT) baselines, particularly in improving complex, low-scoring tutoring scenarios. Crucially, the distilled experiences exhibit robust generalization across diverse model architectures and mathematical datasets.

Abstract: Large language models (LLMs) are increasingly involved in family education, yet HCI has not systematically explained the educational interactions that emerge around them. This scoping review analyzes 53 HCI studies from 6,540 records across 19 venues. Using activity theory and AODM, it relates participants and educational objects to mediation, labour, and rules. We find that the literature centers on child--parent interaction and on language, AI literacy, and relational learning. The introduction of LLMs enabled conversational, embodied, and spatial systems to generate support from the context of an unfolding interaction. LLMs redistributed educational labour, while family and institutional rules left parents and professionals responsible for interpreting outputs and deciding how they entered practice. Evidence across families and educational purposes remains limited, especially on sustained personalization, repair labour, and how families negotiate authority and rules. The review offers a framework explaining how LLM capabilities become organized through family participation.

Abstract: Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mechanism, DLMs operate over an exponentially large exploration space compared to autoregressive models (ARMs), making it challenging to focus on reasoning-guiding tokens under random masking. We define causal shortcuts as token chains that cover the full sequence and provide explicit guidance towards correct reasoning trajectories. We analyze the effects of causal shortcuts on the reasoning accuracy and convergence speed of DLMs, and find that they largely improve answer convergence efficiency and generation accuracy. Motivated by this, we propose a Causal Shortcut Learning (CSL) Framework for DLMs. Specifically, we introduce a step-by-step token extraction procedure to extract causal shortcuts from data, and apply parallel prioritized masking on these tokens during training to enable efficient and accurate convergence to correct answers via causal shortcuts. Extensive experiments across multiple reasoning benchmarks and two base models demonstrate that CSL consistently outperforms existing SFT-variant baselines, achieving an average improvement of $1.92\%$ over SFT-only models, and up to $4.20\%$ on MATH-500. The code is available at the \href{https://github.com/ZJUDianJin/Causal-Shortcuts-Learning}{https://github.com/ZJUDianJin/Causal-Shortcuts-Learning

Abstract: The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using Bloom Classifier models is a promising approach to assess educational materials at scale. These models show high accuracy within-distribution dataset (IID Dataset). However, applying the same models to new out-of-distribution (OOD) datasets such as AI-assisted generated questions could show performance degradation. To identify robust classifiers under dataset shift, we evaluated traditional Machine Learning (ML), transformer, and Large Language models on the Bloom level classification task. We also explored feature-engineering strategies incorporating NLP metrics, appending the learning objectives as part of the input, and text splicing to stabilize OOD performance. Our baseline tests show that TFPOS-IDF ML models perform poorly on OOD (Macro F1-score 0.48) compared to BERT (0.55) and LLMs (0.79). Text splicing improved macro F1-score performance of ML and BERT models (0.59 and 0.62, respectively). Appending the learning objectives with the input increased model performance on specific dataset. Model retraining provided the largest improvement across models and datasets. Overall, these findings highlight the trade-off on the use of pre-trained models with novel AI-assisted educational questions and how strategic feature enhancements help address loss in performance.

Abstract: This paper presents a multi-source classroom study conducted during a 10-week quarter in data science courses at Drexel University. We first investigate the behaviors of student engagement with large language models (LLMs) using four surveys across three data science courses. Second, we evaluate the construct validity of multiple-choice questions (MCQs) generated by an LLM for in-lecture retrieval practice. Based on 378 authored questions (311 deployed, producing 7{,}888 student responses), we analyze whether the difficulty ratings assigned by an LLM match empirical item difficulty. Our study shows that student engagement with LLMs varied across courses and increased over the term. Although students expressed high satisfaction and reported saving considerable time, their perception of deep learning benefits declined, and many noted a tendency toward over-reliance. Regarding the difficulty ratings of LLM-generated MCQs, the Easy, Medium, and Hard labels correlated closely with its assigned Bloom's Taxonomy levels (Spearman $ρ=0.90$), reflecting an artifact of co-generation. However, neither metric predicted empirical item difficulty (difficulty label $ρ=0.06$; Bloom level $ρ=0.02$). The ratings reflect the structural formatting of a question rather than its underlying difficulty.

Abstract: Large language models have allowed the rapid deployment of pedagogical annotations corresponding to constructs of interest, allowing a natural language interface for generating classifications on a conversational dataset. However due to the opaque nature of LLM reasoning, we have no verifiable, mechanistic insight into why a model chose a label for an utterance. We introduce the EduBehaviors framework, an interpretable, scalable approach to annotating educational data that uses LLMs to measure repeated observable behaviors relevant to many constructs of interest and then learns a classifier for the construct based on these observable behaviors. We evaluate the framework on the TalkMoves dataset, predicting the Teacher TalkMoves labels. Our best configuration results in a macro-F1 of 0.673 and 0.688 Cohen's kappa, proving competitive with direct prompting approaches. In addition, we release EduBehaviors Toolkit, two tools allowing researchers to operationalize the EduBehaviors framework in their own data.

Abstract: Engagement-aware learning systems could provide hints or adjust pacing when learners struggle. Prior engagement sensing work distributes sensors across or outside the body rather than consolidating them at one site, or reduces engagement to shared affect or a single dimension (from behavioral, emotional, and cognitive engagement). We introduce E3Sense, a head-worn platform that co-locates electroencephalography, eye tracking, and electrodermal activity to personalize engagement measurement. During a lab study we collected 450 ratings of engagement levels on a five-level ordinal scale while participants watched educational videos. For fifteen held-out participants, E3Sense achieved a within-one-level prediction score of 75.0%, compared with 63.0% for always predicting the most common rating. In an exploratory analysis of 18 participants from the same study who defined engagement, conditioning on learners' definitions raised the same measure by 6.9 points, from 64.6% to 71.5%. Our work provides a proof-of-concept of a head-site, personalized multimodal sensing of engagement for adaptive educational interfaces.

Abstract: Simulating student personas with large language models (LLMs) enables scalable evaluation of educational systems. However, behavioral drift, a progressive decline in persona consistency, can emerge over extended conversations, limiting the validity of such simulations. We evaluate five prompt-level mechanisms using separate monitoring and intervention pipelines. Across 1,200 28-turn conversations spanning four LLMs and two ADHD persona intensities, we varied when to intervene (static vs. adaptive) and what to inject (reinjection vs. reflective reminder), plus a novel adaptive condition in which a monitor generates behavior-specific instructions. Relative to no intervention, reinjection reduced the modeled rate of LLM-rated drift by 35--38\%, reflective reminders by 22--27\%, and behavior-specific instruction by 87\%. None eliminated drift. We found no evidence that adaptive timing outperformed static scheduling. Monitoring therefore appears more useful for deciding \textit{what} to correct than \textit{when} to intervene, although behavior-specific instruction requires component-level testing.

Abstract: Social Stories are widely used to support autistic children in understanding and preparing for everyday situations, but creating stories that are appropriately tailored to each child's needs remains labor-intensive for practitioners. Existing digital tools support story assembly and delivery, but much of the work of writing, visual preparation, and personalization remains manual. Recent AI-based approaches have enabled automated story generation, yet offer limited support for practitioner oversight, context-sensitive personalization, and the use of supportive visuals grounded in individual learner profiles. We present AdaptED Stories, a practitioner-guided system for authoring, personalizing, and delivering Social Stories in special-education contexts. The system uses student profiles to draft story text and visuals, supports review and refinement by practitioners, and includes reading-session support with comprehension activities and session records. We report findings from a practitioner-informed design process, assessments of generated stories and visuals, and a usability study with seven special-education practitioners. Our findings suggest that AI assistance can reduce story-preparation burden and support more individualized story creation, alongside the importance of practitioner oversight, cultural and contextual specificity, and designing for varied learner needs. These findings contribute design implications for AI-assisted accessibility tools in special-education.

Abstract: Students increasingly study alongside generative artificial intelligence (AI), yet unguided access to fluent answers invites cognitive offloading, and there is little evidence on which configurations of AI tutoring produce learning. Two design margins are usually bundled together: pedagogical structure (how the tutor teaches) and interaction modality (how students talk to it). We separate them. In a preregistered randomized field experiment in a graduate corporate-finance course of an online MBA, we randomized 86 students between a structured tutor grounded in the course materials and a holdout in which consumer AI remained freely available. Within the tutored arm, each student's channel alternated weekly between voice and text, so the modality effect is identified within student. Structure mattered: tutored students gained 6.63 points more than ability-matched peers (p=.007), and the gain was concentrated in written reasoning, where the share of answers reaching relational quality rose from 8% to 49% in the tutored arm against 8% to 27% in the holdout. Modality did not matter for learning. The instructor's own final, on file for all 86 randomized students, shows the same direction (2.6 points of 100, with no difference on a pre-treatment midterm). Voice nearly doubled conversational interaction and cost 2.8 times as much to deliver, yet it produced weekly mastery statistically equivalent to text, even as students came to prefer it. Pedagogical structure shapes what students practice, and modality shapes how they interact with the tutor. Making an AI more humanlike does not by itself make it more educational.

Abstract: As deep learning models continue to advance, knowledge tracing models have achieved higher accuracy. However, these gains come at the cost of reduced interpretability, which is crucial for practitioners in educational settings to adopt new methodologies. Additionally, deep learning models are prone to overfitting, particularly when dealing with the small datasets that are common in educational applications. In this paper, we propose a novel regularization technique designed to enhance the robustness of deep-learning-based knowledge tracing models, while simultaneously improving their interpretability. Our method addresses both the interpretability and overfitting challenges, making it more feasible for real-world educational applications.

Abstract: Learning analytics dashboards (LADs) are intended to help students make sense of their learning data to support reflection and decision-making. However, their visualisations can be complex, particularly for students with low visualisation literacy. Narrative techniques, such as annotated charts and data comics, have been used to communicate insights directly, but not as supplementary materials to empower students to explore their visualisations themselves. In response, we conducted a qualitative study examining how data comics can complement LADs. We interviewed 18 nursing students and 4 of their teachers about a multimodal LAD containing visualisations with data comics explaining them. Analysis showed that data comics were clear, engaging, and helped make complex visualisations more accessible, though they must be carefully designed to avoid overwhelming students with information. The findings suggest that both students and teachers are receptive to data comics as a means of supporting the interpretability of LADs.

Abstract: Generative AI (GenAI) can support open-ended learning through generation, personalization, and learner modeling, yet educators need ways to shape these capabilities around educational goals. Through interviews and design activities with 15 U.S. educators, we examined educator configuration of GenAI using K-12 career exploration as an exploratory context. Educators configured not only AI-generated experiences, but also when student activity became an inference, whether learner information persisted, who could access it, and how it informed subsequent human action. They also faced challenges translating teaching needs into configurations: recognizing possibilities for control beyond familiar uses of GenAI, decomposing general-purpose AI into understandable functions and responsibilities, and identifying useful information through intended teaching actions. We discuss how GenAI systems can support educators in expressing and testing configurations, while establishing boundaries around personalization, inference, persistence, disclosure, and action to keep AI-supported learning aligned with evolving learner needs.

Abstract: Large vision-language models have achieved remarkable progress in multi-modal understanding, yet their capabilities in educational settings remain insufficiently evaluated. In AI-assisted language learning, models must interpret artistic imagery, understand its semantic, affective, and cultural content, and reason about visual context to support meaningful interaction. However, existing benchmarks primarily focus on real-world images or domain-specific educational reasoning, providing limited coverage of artistic educational content. To address this gap, we introduce MUSE, a benchmark for evaluating large vision-language models on artistic image understanding in situated educational applications. MUSE decouples image annotation from question generation, enabling diverse tasks with controllable difficulty while reducing annotation effort. It comprises twelve tasks spanning visual perception, semantic and affective interpretation, culture understanding, and compositional reasoning, together with diverse artistic images deliberately curated to center Singaporean and Southeast Asian multicultural contexts alongside Western art traditions, covering multiple themes and difficulty levels. Evaluation of open-source and proprietary models reveals substantial disparities across capability dimensions, particularly in affective interpretation and compositional reasoning. Our analysis further identifies common failure modes and key challenges for developing trustworthy multi-modal models for education. We hope MUSE will serve as a standardized benchmark for advancing multi-modal understanding in situated educational applications.

Abstract: Generative AI has become a routine resource in programming education, and most institutional responses to it are attempts at control, either by restricting access or by offering students a controlled version of the technology. This paper reports a seven-week mixed-methods pilot study in a master's-level data analytics course, in which 33 students were randomly assigned either to a scaffolded AI Study Coach embedded in the notebook-based laboratory sessions or to unrestricted use of AI tools of their own choosing. The Coach offered stepwise hints, did not generate code, limited the number of hints per session, and required a short reflection at the end of each session. The design assumed, in line with scaffolding theory and recent experimental evidence, that guided and limited support would build confidence and reduce over-reliance, and that the scaffolded group would learn more. Assignment performance did not differ between the conditions. Students in the Coach condition reported higher confidence but managed the hint budget poorly, while students in the unrestricted condition were satisfied with their tools and uneasy about how much they depended on them. In interviews, students in both conditions identified awareness of their own reliance on AI as the most valuable outcome of the course. Students who had formulated their own rules for when to use AI performed better in both conditions, and those with the best understanding of how the models work, in every case self-taught, used the tools most deliberately and achieved the highest scores. The design of the tool mattered less than the students' capacity to govern their own use of it, a capacity that is at present acquired by chance. The paper argues that the appropriate response is structural: assessment that grades the reasoning behind AI-assisted work, and AI literacy taught explicitly as a core skill.

Abstract: A child with reduced distance vision often does not know that anything is wrong. Children adapt, move closer, and rarely report the difficulty, so the problem can survive years of schooling before an adult notices. School screening addresses part of this, but it runs on a schedule, depends on staffing, and is separated from the classroom moments where the difficulty appears. Smartphone and web-based acuity tests have widened access, yet every one of them still needs somebody to start a test. We present SightSentinel, an architecture that turns a wall display a child already reads from into a recurring screening site. Ordinary educational content carries short calibrated optotype probes, and eight specialized agents divide the work. Perception agents recover viewing distance, recognition accuracy, approach behavior, gaze stability, response latency, and interocular difference from each encounter. A quality agent discards observations taken under bad geometry, poor lighting, or inattention. A longitudinal agent accumulates only the surviving evidence against the child's own baseline, and an orchestrator reports a Vision Concern Score routed through a safety gate whose output range excludes diagnosis, refraction, prescription, and reassurance. The design question is whether many cheap, noisy, well-gated encounters can reach a referral decision that one scheduled test reaches late or misses. We state the formulation, the architecture, a four-stage validation protocol against clinical reference standards, and the conditions under which the approach should be rejected.

Abstract: The CRITICS project addresses science accessibility and literacy by converging advanced Machine Translation (MT) based on Large Language Models (LLMs) with educational technology. By leveraging MT systems specifically optimized for scientific content, educational institutions can provide accurate, culturally relevant translations of scientific materials in students' native languages, ensuring that complex scientific concepts are comprehensible while maintaining technical accuracy. Building on these translations, the project explores the design and evaluation of innovative science teaching-learning proposals grounded in curriculum-aligned teaching-learning. Thus, CRITICS will investigate key components of scientific argumentation and critical thinking practices together with textual feedback aligned with learning objectives and assessment criteria inspired by competence-based evaluation frameworks. CRITICS aims to break down language barriers to accessing cutting-edge research and educational materials currently available only in high-resourced languages, thereby facilitating the democratization of scientific knowledge and fostering critical thinking in science education.

Abstract: Large language models (LLMs) are increasingly deployed as tutors, but it is unclear whether they support all students equally well. We introduce \textbf{EduFair-Bench}, a benchmark for auditing the pedagogical fairness of LLM tutors---whether tutoring quality varies systematically with student demographics. EduFair-Bench pairs a multi-domain question bank (mathematics, physics, chemistry) with a controlled simulation in which a fixed LLM student interacts with each tutor across nine demographic levels spanning four dimensions: gender, immigration background, first language, and socioeconomic status (SES). Tutoring quality is scored on five turn-level pedagogical metrics and four conversation-level dimensions, using an LLM judge validated against three-annotator consensus on 180 tutor turns. Bias is measured via paired Wilcoxon signed-rank tests and bootstrap effect-size confidence intervals. Two ablations (demographic cues conveyed through names; conflicting demographic information between tutor and student) disentangle tutor-driven from student-driven bias. Across five tutors, we find that model capability and demographic fairness are largely orthogonal: the smallest model is the most consistent while the four more capable tutors all exhibit wide demographic gaps with no clear capability-to-fairness ordering, pedagogy-specific RL training redistributes rather than removes bias, and language- and immigration-related cues produce larger gaps than gender- and SES-related cues.

Abstract: While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructing auxiliary lines, spurring the rise of Visual Chain-of-Thought (VCoT). However, existing evaluations typically assess visual generation quality and final answer accuracy in isolation, failing to examine whether intermediate visual aids are geometrically valid, effectively utilized in subsequent reasoning, or causally responsible for task success. To bridge this gap, we introduce GeoVAD-Bench, a diagnostic benchmark that pairs a fine-grained five-dimensional trajectory diagnosis covering perception, auxiliary quality, utilization, deductive reasoning, and final correctness with controlled No-Aux, Auto-Aux, and GT-Aux intervention settings to systematically isolate intermediate error modes, the causal gains of visual aids, and the resulting autonomy gap. Our findings reveal that while high-quality auxiliary aids offer substantial theoretical gains for geometric problem solving, autonomous generation is frequently hampered by compounding errors across geometric perception, faithful visual manipulation, visual-state grounding, and deductive reasoning. Guided by these diagnostic insights, we establish a specialized data construction pipeline encompassing geometric perception, diagram editing, and interleaved visual-textual reasoning trajectories, and develop a progressive SFT and multimodal RL training framework. The resulting model, GeoWeave-8B, outperforms the base model by +25.3% in final geometric accuracy and achieves a +30.4% gain in process average across the four intermediate diagnostic dimensions.

Abstract: Blind or low vision (BLV) students are less likely to graduate from college, particularly in computing. Prior work documents accessibility challenges in high school and college, but we lack understanding of the transition process that produces this "leaky pipeline." To address this, we interviewed ten BLV college students about going to college to study computing. We analyzed our data through the lens of life transition, specifically Intersecting Liminality. Our findings reveal that some BLV students face such immense digital accessibility and college acclimation barriers that the only way forward as coders is to take on a "second job" as a blind advocate or drop out of the computing major. We argue that the college transition is a critical point for analysis and technological intervention, and further, that Intersecting Liminality provides a useful lens for HCI scholars to unpack the compounding challenges that prevent some BLV students from completing computing degrees.

Abstract: As artificial intelligence (AI) rapidly iterates and transforms teaching, learning, and knowledge production, philosophical reflection has become increasingly indispensable to educational debates that remain predominantly shaped by Western intellectual traditions. This article proposes Daoism as an alternative philosophical framework for reimagining AI in education. Through philosophical analysis and textual interpretation of classical Daoist sources, brought into dialogue with contemporary scholarship on AI in education, it examines how the Daoist concepts of "Dao nature," "self-cultivation," and the "Zhenren" address fundamental questions concerning reality, the epistemic aims of education, and ethical action in the AI-mediated era. In doing so, the article diversifies the philosophical voices shaping inquiry into AI and education, enriching the field's conceptual resources for grappling with the philosophical questions AI raises for education and offering a genuinely pluralistic foundation for comparative philosophy of education in the AI era.

Abstract: The rapid adoption of generative AI tools such as ChatGPT has sparked intense debate about their risks and opportunities for education, as well as the ways researchers should investigate them. In this paper, we approach these discussions through an analogy with the Thermomix, a smart kitchen appliance that has similarly provoked both enthusiasm and critique. By mapping Thermomix use cases onto examples of learning with generative AI, and situating them within the ICAP and SAMR frameworks, we show how different modes of tool use can either support or undermine meaningful engagement and learning. The Thermomix metaphor underscores that the central question is not whether learners employ AI, but how such use shapes their learning processes. In doing so, we provide a conceptual lens for researchers and practitioners to critically examine - and more effectively guide - the integration of generative AI into educational practice.

Abstract: Representational fidelity is routinely treated as a single abstract-realistic continuum, a simplification that limits how it is described and compared across research and design contexts. We introduce a multidimensional design space of representational fidelity for didactic visualization in science & engineering, inductively derived from a 175-item corpus spanning several disciplines, modalities, and instructional aims. The resulting design space specifies five dimensions: Morphological, Dynamic, Cueing, Contextual, and Interactive Fidelity, with seven sub-dimensions. We demonstrate the design space's descriptive power through successive rounds of expansion and refinement and analyze the corpus to reveal relationships among dimensions and implications for design and research. We further validate the design space through a pilot focus group in which participants applied the dimensions in an open-ended design exercise. Resulting sketches and verbal rationales informed a single-designer applied case study, offering preliminary evidence of the design space's generative potential as a structured aid to design exploration. Together, these contributions lay the groundwork for future research and more intentional design practice.

Abstract: The hype around generative AI seems to promise unprecedented productivity (and learning) gains. However, these technologies' increasing agentic features seem to push learners towards individualism (or individual isolation), over-reliance, and dependence on them. Human-centered design approaches (e.g., value-sensitive design) assume that, by unearthing human needs, preferences, and values, technology researchers/designers may avoid such dangers, which are driven by wider systemic factors like economic incentives or inherent human limitations (e.g., our tendency to seek, in the moment, the easiest path of action). Yet, so far these efforts seem insufficient to guide our design of educational technology that avoids the aforementioned dependency and isolation dangers, while finding widespread adoption. This paper presents an alternative, more emancipatory vision for future educational AI technology, oriented towards learner flourishing while considering the wider complex systems they inhabit, including tentative design principles and an overall design methodology. Yet, many open questions remain before this vision can be realized.