IEEE Transactions on Learning Technologies最新文献

{"title":"Codevelop Learning Tasks With Generative AI: Mapping Challenges, Gains, and Professional Development Needs","authors":"Jie Cao;Shuman Wang;Xian Chen;Christian Schunn","doi":"10.1109/TLT.2026.3675467","DOIUrl":"https://doi.org/10.1109/TLT.2026.3675467","url":null,"abstract":"The design of learning tasks represents a fundamental pedagogical process that directly shapes educational effectiveness, but this process is time-consuming and knowledge-intensive for teachers. The rapid emergence of generative artificial intelligence (GenAI) technologies has created unprecedented opportunities for supporting teachers’ teaching practice. However, despite growing interest in teacher–GenAI collaboration, current research primarily focuses on preservice teachers and overall lesson plan design, with limited attention to challenges inherent in teacher–GenAI codesign of learning tasks or what teachers learn from such collaboration. To address this gap, we employed a mixed-methods approach involving 28 in-service teachers who collaborated with GenAI tools to codevelop learning tasks across three weeks. Qualitative analyses identified four overarching interaction challenges: inefficient interactions, low-quality tasks, lack of distributed cognition, and negative human–GenAI feedback loops. These overarching challenges emerged from bilateral deficiencies—three teacher-related shortcomings (providing too little context information, providing too little pedagogical guidance, and lacking GenAI skills) and six GenAI-related shortcomings (accuracy issues, limited prompt understanding, weak knowledge of content sequences, limited context knowledge, incomplete instructional solutions, and usability issues). Quantitative analyses of changes from pre to post showed significant improvements in teachers’ technical knowledge and artificial intelligence (AI) literacy, with no changes in self-efficacy and pedagogical knowledge. Finally, teachers expressed professional development needs primarily in two areas: AI foundations and applications and AI pedagogy. This study provides empirical evidence of bidirectional challenges in teacher–GenAI collaboration in designing learning tasks and offers a framework for understanding teacher professional growth through AI collaboration and further needs.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"215-228"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147665448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Dual-Agent Intelligent Tutoring System for Teaching Two-Step Fraction Word Problems","authors":"Chih-Chia Chang;Shu-Chuan Shih;Bor-Chen Kuo","doi":"10.1109/TLT.2026.3708780","DOIUrl":"https://doi.org/10.1109/TLT.2026.3708780","url":null,"abstract":"This study developed a dialogue-based math intelligent tutoring system. Two tutoring modules—single-agent and dual-agent—were implemented based on the AutoTutor framework to support seventh-grade students in learning two-step fraction arithmetic through word problems. In the single-agent module, the agent plays the role of a teacher, whereas in the dual-agent module, an additional agent plays the role of a peer student who interacts with the learner. To support adaptive instruction, a block-based matching method was applied to analyze students’ responses, allowing the system to deliver feedback tailored to each student's performance. Diagnostic pedagogies include provoking cognitive conflict, problem simplification, representational teaching, and vicarious learning were incorporated into the instructional design. The developed system can be used for remedial instruction. A quasi-experimental study was conducted to compare the learning effectiveness among single-agent tutoring, dual-agent tutoring, and traditional teacher-led remediation. The experimental results indicated that dual-agent tutoring significantly outperformed the single-agent tutoring. These preliminary findings suggest that, within the current quasi-experimental context, a dual-agent design incorporating peer interactions shows potential for enhancing learning effectiveness compared to a single-agent approach.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"636-647"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11592148","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing Interbrain Synchrony in Student Dyads During Collaborative Problem-Solving via Hyperscanning EEG","authors":"Chun-Hsiang Chuang;Ting-Yu Hsu","doi":"10.1109/TLT.2026.3703810","DOIUrl":"https://doi.org/10.1109/TLT.2026.3703810","url":null,"abstract":"Effective collaboration is essential for learning, especially when performing tasks that demand logical reasoning and problem-solving. Understanding how knowledge is coconstructed between individuals can enable valuable insights into the underlying cognitive processes. As teamwork increasingly shifts to online environments, there is a pressing need to investigate the dynamics of participant interaction beyond observable behaviors in depth. This study used a hyperscanning electroencephalography (EEG) approach, one of the most commonly used methods in social interaction research, to investigate interbrain synchrony (IBS) between dyads performing high school-level mathematics and computational thinking tasks of varying difficulty in a setting designed to simulate remote communication. IBS was predominantly observed in the frontal, temporal, and parietal regions and varied significantly across most frequency bands with respect to both task difficulty and completion time. Interestingly, an inverted U-shaped relationship emerged between IBS and task difficulty, with the highest synchrony observed during tasks of moderate complexity, suggesting that a balanced cognitive challenge may be optimal for promoting neural alignment. For the most demanding tasks, however, IBS was positively associated with longer completion times, implying that extended engagement with high-difficulty tasks may encourage sustained collaborative effort and neural coupling. These findings highlight IBS as a potential neural marker of effective joint problem-solving and shared cognitive engagement during collaborative tasks. This study has implications for educational design, team-based learning, and the development of neuroadaptive tools to enhance remote collaboration.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"609-619"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multidimensional Influences on College Students’ Computational Thinking: An Empirical Study in Visual Programming Environments","authors":"Xiangping Cui;Chen Du;Ying Gao;Yajuan Cheng;Shujia Fan;Jun Shen","doi":"10.1109/TLT.2026.3716861","DOIUrl":"https://doi.org/10.1109/TLT.2026.3716861","url":null,"abstract":"The cultivation of computational thinking (CT) among college students represents a critical imperative for both individual advancement and societal development in the digital age. Although existing research has established the positive impact of visual programming on CT development, a comprehensive examination of the factors influencing CT within visual programming environments remains insufficient. To address this research gap, this study integrates the achievement goal theory and triadic reciprocal determinism to develop a novel theoretical framework. Through rigorous pilot expert consultation processes, eight key factors affecting students’ CT were identified: programming literacy, self-efficacy, learning engagement, academic self-regulation, learning support, teaching strategies, course quality, and visual programming presentation. Based on these factors, we constructed and empirically validated a hypothesized model of CT development in visual programming environments. Using pragmatic survey data from college students and structural equation modeling techniques, we tested our hypotheses and validated the proposed model. The findings reveal that learning support significantly enhances self-efficacy; teaching strategies, course quality, and visual programming presentation substantially promote learning engagement and academic self-regulation; and seven of the eight factors (excluding programming literacy) exert significant positive influences on CT development. Based on these findings, we propose three practical recommendations: cultivating student interest as a primary driver of CT development, promoting continuous professional development among instructors, and integrating AI-enhanced approaches into curriculum design. This study advances our comprehensive understanding of how visual programming environments facilitate CT development and provides actionable insights for educational practice in higher education contexts.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"778-790"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148748541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Co-Creating a Community-Focused Educational Knowledge Graph for Trustworthy Language Knowledge: A Case Study on Yanyuwa","authors":"Lele Sha;Zhiping Liang;Zijie Zeng;Dragan Gašević;Guanliang Chen;Gloria Milena Fernández-Nieto;Yi-Shan Tsai;Zachari Swiecki;Alice Gaby;John Bradley","doi":"10.1109/TLT.2026.3694962","DOIUrl":"https://doi.org/10.1109/TLT.2026.3694962","url":null,"abstract":"This study explores how educational technology can support endangered language education, with a focus on Australia’s critically endangered Indigenous Yanyuwa language. Employing community-focused approaches involving Yanyuwa educators, we collaboratively pioneered an innovative educational knowledge graph (KG) that embeds a rich collection of language data from prior documentation and preservation efforts to assist with language learning. Our study reveals that despite the significant challenges posed by shortages in linguistic expertise and advanced computational models, a semantic KG can be built for trustworthy language knowledge retrieval by leveraging a semisupervised semantic labeling approach. Distinct from prior KGs relying solely on technicians, we show that it is feasible to include key community stakeholders at the ontological design and feedback phases, ensuring that the KG is tailored to communities’ knowledge needs and priorities. We further demonstrate the KG’s educational utility through visualizing the retrieved subgraph as a prototype starting point for co-designing language learning materials with teachers. Our approach is language-agnostic and may offer a generalizable framework for empowering marginalized communities through trustworthy learning technologies.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"584-597"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148442430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AEED: Agentic Edge-AI Engagement Detection for K-12 Classrooms","authors":"Isaac Arnold;Eva Burch;Shenghua Zha;John F. Shelley-Tremblay;Na Gong","doi":"10.1109/TLT.2026.3724409","DOIUrl":"https://doi.org/10.1109/TLT.2026.3724409","url":null,"abstract":"Monitoring classroom participation requires dependable, low-latency, private solutions that work within edge hardware constraints while maintaining meaningful learning connections. On-device inference is conceivable with edge-AI systems, but they rarely analyze input signal importance in real-world classroom scenarios and employ face orientation or gaze as crude proxies. The embodied cognition theory predicts that engagement should be represented in whole-body sensorimotor activity on specific tasks, not only in face configuration, but agentic classroom pipelines have not operationalized this requirement. In this article, we present agentic edge-AI engagement detection (AEED), a cross-disciplinary pipeline that leverages classroom deployment constraints to inform model design, data collection, and system development. In particular, AEED consists of BodyPosture (BP), a model trained on traditional camera-facing body-orientation cues, and FaceReaction (FR), a face model with labels derived from synchronized EEG, ECG, and task performance. In order to examine the impact of input design alongside architectural and platform characteristics, both models operate in parallel under the same tracking, hardware, and logging settings. The pipeline uses commodity edge hardware for interaction recording, dual-model inference, and anonymous student tracking. When camera geometry changes, BP's orientation-based signals invert, whereas FR's physiologically grounded signals correlate with learning outcomes in contexts similar to its training conditions. These results suggest that input design and label construction may matter more than architectural choice for deployment validity, although training-domain differences between the two models remain a partial confound. For agentic AI systems in authentic classrooms, these findings offer a reproducible framework for building embodied, per-student engagement trajectories.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"863-876"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149033596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Auto-TSCD: Automated Discovery of Interpretable Temporal Cognitive Diagnosis Rules for Intelligent Tutoring Systems","authors":"Yifei Sun;Mingkai Duan;Sicheng Hou;Shi Cheng;Maoguo Gong;Zhi-Hui Zhan","doi":"10.1109/TLT.2026.3729582","DOIUrl":"https://doi.org/10.1109/TLT.2026.3729582","url":null,"abstract":"Accurately tracking students’ evolving knowledge states is a key requirement for intelligent tutoring systems and adaptive learning platforms. Existing deep knowledge tracing models can capture temporal learning patterns, but their hidden states and gating mechanisms are often difficult to inspect. We propose Auto-TSCD, a focused extension that combines target-aware temporal representations with computational-tree search to discover structurally inspectable temporal cognitive diagnosis rules. Candidate residual rules are represented as computational trees over learned or model-derived inputs, including student and exercise embeddings, a historical-state representation, and target-aware temporal similarity. A probabilistic model-building strategy searches for rules that balance validation performance and structural simplicity, and the selected rule is reported as an explicit mathematical formula. Experiments on three real-world educational datasets show that Auto-TSCD obtains the highest mean AUC in the reported comparison, with modest gains of approximately 0.65–0.85 percentage points over the directly related TSCD and PMB-CAS models. On ASSISTments-09, PMB-CAS retains better ACC and RMSE. The explicit tree exposes which model-derived representations and operators enter the prediction, providing structural transparency; semantic and teacher-facing interpretability remain to be validated.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"925-937"},"PeriodicalIF":7.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149188479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal Conversational Emotion Recognition in Education With Uncertain Missing Modalities: A Graph Fusion Network Approach","authors":"Juan Yang;Ruinan Shi;Xu Du;Yiqian Xie;Weiwei Wang","doi":"10.1109/TLT.2026.3691830","DOIUrl":"https://doi.org/10.1109/TLT.2026.3691830","url":null,"abstract":"Multimodal emotion recognition in conversations (MERC) under uncertain missing modalities remains a critical challenge, especially in educational contexts. Significant research efforts have been dedicated to developing novel solutions to tackle this problem. Nevertheless, existing methods are difficult to fully utilize available information for high-quality data reconstruction, and fail to learn discriminative multimodal representations for handling uncertain missing modalities. Furthermore, the generalization of such methods in educational contexts remains largely overlooked. To address these challenges, this study proposes a novel graph fusion network approach for achieving MERC tasks in education with uncertain missing modalities. Our method first reconstructs missing modalities by using adaptive fusion weights to aggregate information from the most similar neighbors in the available modalities. The reconstructed data are processed via a mask-aware graph structure to explicitly exploit masked cues to enhance the robustness of intramodal representations. Initial multimodal fusion representations derived from single-modal features are employed to build a dual-graph structure for further refining the multimodal representation learning of each utterance. During the training process, our method also introduces the boundary-aware contrastive learning to enable the accurate identification of samples near decision boundaries. Experiments on three multimodal datasets, including one self-collected educational dataset, CMU-MOSI, and CMU-MOSEI, demonstrates its superiority, effectiveness, and generalizability.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"492-504"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148171737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IAEAgent: LLM-Based Educational Agent for Instructional Alignment Evaluation in University Courses","authors":"Junqi Liao;Minjuan Wang;Xiaofei Wu;Yizhi Wang;Xin Wei","doi":"10.1109/TLT.2026.3695576","DOIUrl":"https://doi.org/10.1109/TLT.2026.3695576","url":null,"abstract":"In university courses, instructional alignment evaluation reflects the degree of alignment between the intended teaching requirements and the actual content delivered by teachers. It can not only provide university administrative departments with evidence about actual teaching performance but also facilitate teachers’ targeted reflection and continuous instructional improvement. However, there is still a lack of a theory-grounded, course-aware, and quantitatively interpretable instructional alignment evaluator. To address this issue, in this article, we propose a new evaluation paradigm—a large language model (LLM)-based educational agent (IAEAgent)—for instructional alignment evaluation in university courses. First, by injecting teaching materials such as textbooks using parameter-efficient fine-tuning, a course-specific LLM with in-depth disciplinary comprehension is constructed. Then, based on this LLM and employing prompt engineering, the intended and actual instructional knowledge graphs (KGs) can be, respectively, extracted from teaching requirement documents and teachers’ actual audio transcripts of a lesson. Subsequently, guided by teaching quality evaluation theories, a quantitative analysis of instructional alignment is conducted for these two KGs across three crucial dimensions: knowledge coverage completeness, knowledge depth consistency, and knowledge structure coherence. Finally, based on the obtained analytical results, a teaching quality evaluation report containing teaching diagnostics and improvement suggestions is generated. Extensive experiments demonstrate that the IAEAgent excels in comprehensive and fine-grained instructional alignment evaluation. Furthermore, ablation studies validate the effectiveness of each step within the IAEAgent.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"505-519"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148236173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving Automated Feedback Systems for Tutor Training in Low-Resource Scenarios Through Data Augmentation","authors":"Chentianye Xu;Jionghao Lin;Yujing Zhang;Tongshuang Wu;Vincent Aleven;Kenneth R. Koedinger","doi":"10.1109/TLT.2026.3665740","DOIUrl":"https://doi.org/10.1109/TLT.2026.3665740","url":null,"abstract":"Tutoring is an effective instructional method for enhancing student learning, yet its success relies on the skill and experience of the tutors. This reliance presents challenges for the widespread implementation of tutoring, particularly in training novice tutors. To support tutor training programs, real-time automated feedback systems are essential for efficiently training large numbers of tutors. A recent study employed generative pretrained transformers (GPTs) for sequence labeling to identify desirable and undesirable praise components in a tutor training dataset, providing explanatory feedback. However, this approach requires a significant amount of labeled data for fine-tuning, which is both labor-intensive and dependent on expert input. To address the challenges associated with extensive data labeling, the current study explores the use of prompting more advanced GPT models such as GPT-4o to generate synthetic datasets for augmenting labeled response data, followed by fine-tuning a GPT-3.5 model. Our results show that fine-tuning GPT-3.5 on a GPT-4o-generated augmented dataset of 520 instances yields statistically meaningful improvements in the identification of praise components. Specifically, the <inline-formula><tex-math>$F_{2}$</tex-math></inline-formula> score increases by 20.5% for effort-based praise and by 17.3% for outcome-based praise relative to the same model fine-tuned without data augmentation. Moreover, the proposed data augmentation approach exhibits effective generalizability to the identification of additional praise categories, specifically person-based praise. When fine-tuned on an augmented dataset of 520 instances, the model achieves a 16.5% improvement in the <inline-formula><tex-math>$F_{2}$</tex-math></inline-formula> score for person-based praise, accompanied by increases of 19.9% in modified intersection over union score and 21.6% in intersection over union score, relative to the same model fine-tuned without data augmentation. These findings suggest that for data-intensive tasks, synthetic data generated through GPT model prompting can substantially enhance fine-tuned model performance in low-resource scenarios. This approach offers a scalable and cost-effective solution to alleviate the reliance on extensive expert-labeled data, enabling broader adoption of automated tutor training systems and facilitating the rapid development of skilled tutors at scale.","PeriodicalId":49191,"journal":{"name":"IEEE Transactions on Learning Technologies","volume":"19 ","pages":"166-181"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147557988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}