论文检索

Hendrik Baier, Mark T. Keane, Sarath Sreedharan, Silvia Tulli, Abhinav Verma

In this paper, we highlight the field of explainable sequential decision making. We discuss how the problem of explaining sequential decisions gives rise to problems and challenges that are absent from scenarios that focus on explaining single-shot decision making. We provide a short survey of some of the more prominent subareas within explainable sequential decision-making and their unique focuses and blind spots. Here, we argue that we need to go beyond simply focusing on individual subareas like explainable planning, reinforcement learning, or robotics, and move towards studying and tackling the more general problem of explainable sequential decision-making. Such a holistic approach will not only allow us to identify previously ignored problems, but also provide us with the ability to transfer ideas and intuitions from one subarea of explainable sequential decision-making to another. We end the paper with a discussion on future directions and some of the most pressing open questions.

Todd W. Neller, Steve Geinitz, Kevin Wang, Zach Dodds, Nicholas Dodds, Ryan O Connor, Aimen Taha, Ananta Manoranjan, Saurabh Ray, Deepak Ajwani 等

The Model AI Assignments session seeks to gather and disseminate the best assignment designs of the Artificial Intelligence (AI) Education community. Recognizing that assignments form the core of student learning experience, we here present abstracts of eight AI assignments from the 2026 session that are easily adoptable, playfully engaging, and flexible for a variety of instructor needs. Assignment specifications and supporting resources may be found at \url{http://modelai.gettysburg.edu}.

Wanlu Zhang, Jia Zhu, Xi Yang, Weijie Shi, Yue Cui, Xinle Dai, Jiewen Sun

Classroom exercises are imperative for reinforcing learning. However, in conventional instruction, students frequently lack timely and personalized feedback. To address this, we present TacpAgent(Teaching Agent for Classroom Practice),a generative LLM-based agent that delivers detailed, individualized guided feedback to promote self-reflection through a prompt-template framework.In the context of this study, Classroom Practice is defined as the set of structured classroom exercises used for formative assessment.TacpAgent takes as input the teacher-prepared exercises and reference answers, together with students’ submitted responses, confidence levels, and brief explanations, then leverages the DeepSeek LLM with designed prompt templates to generate guided feedback and recommend relevant textbook sections for targeted review. We conducted a three-month quasi-experimental study with two high school classes (N=87). The study compared TacpAgent-supported exercises with traditional paper-based exercises. The experimental group showed significantly higher quiz scores (F=18.516, p＜0.001) and improved emotional (p＜0.001) and behavioral engagement (p=0.003). In contrast, the control group demonstrated no significant changes. The results suggest that TacpAgent may enable scalable, personalized formative assessment in classroom settings and provide practical guidance for integrating generative AI into everyday teaching.

Mengxia Yu, Bang Nguyen, Olivia Zino, Meng Jiang

Educational question generation (EQG) is a crucial component of intelligent educational systems, significantly aiding self-assessment, active learning, and personalized education. While EQG systems have emerged, existing datasets typically rely on predefined, carefully edited texts, failing to represent real-world classroom content, including lecture speech with a set of complementary slides. To bridge this gap, we collect a dataset of educational questions based on videos from real-world lectures. On this realistic dataset, we find that current methods for EQG struggle to accurately generate questions from educational videos, particularly in aligning with specific timestamps and target answers. Common challenges include selecting informative contexts from extensive transcripts and ensuring generated questions meaningfully incorporate the target answer. To address the challenges, we introduce a novel framework utilizing large language models (LLMs) for dynamically selecting and rewriting contexts based on target timestamps and answers in lecture videos. First, our framework selects contexts from both lecture transcripts and video keyframes based on answer relevance and temporal proximity. Then, we integrate the contexts selected from both modalities and rewrite them into answer-containing knowledge statements, to enhance the logical connection between the contexts and the desired answer. Quantitative evaluation and human evaluation show that our approach improves the quality and relevance of the generated questions.

Guoliang Xu, James Corter

Automated short answer grading with feedback (ASAG-F) systems currently face challenges in transparency, pedagogical alignment, and cost-effectiveness that limit their real-world deployment. We introduce GraphRAG, a knowledge graph-based retrieval-augmented generation framework that addresses these limitations by grounding all large language model (LLM)-generated feedback and scores in instructor-curated atomic facts, ensuring traceability and verifiability. Using the Short Answer Feedback (SAF) dataset with 31 topics, we evaluate GraphRAG on unseen-question and unseen-answer splits. Our systematic evaluation demonstrates that GraphRAG achieves grading accuracy comparable to vector-based RAG and generally superior to a fine-tuned LLM baseline model while providing more transparent source attribution. Additional findings include: (1) Instructing the LLM to discretize continuous scores to match pedagogical rubrics, such as the 0.25 increments common in SAF, improves grading accuracy; (2) LLM-generated feedback exhibits length-dependent quality variations when unconstrained; prompt-based length control substantially enhances feedback quality and its stability, achieving optimal balance of instructional richness and conciseness; (3) Performance scaling analysis reveals that basic models like GPT-4o-mini offer cost-effective performance, while premium models like Claude-Opus-4 show diminishing returns. These results demonstrate that GraphRAG offers a robust, explainable, pedagogy-aligned, and cost-effective solution for large-scale educational applications, enabling transparent automated grading with effective pedagogical feedback and practical deployment costs.

Eric Xie, Danielle Waterfield, Michael Kennedy, Aidong Zhang

Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value. To address these limitations, we introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation. SlideBot is organized around three pillars: informativeness, ensuring deep and contextually grounded content; reliability, achieved by incorporating external sources through retrieval; and practicality, which enables customization and iterative feedback through instructor collaboration. It incorporates evidence-based instructional design principles from Cognitive Load Theory (CLT) and the Cognitive Theory of Multimedia Learning (CTML), using structured planning to manage intrinsic load and consistent visual macros to reduce extraneous load and enhance dual-channel learning. Within the system, specialized agents collaboratively retrieve information, summarize content, generate figures, and format slides using LaTeX, aligning outputs with instructor preferences through interactive refinement. Evaluations from domain experts and students in AI and biomedical education show that SlideBot consistently enhances conceptual accuracy, clarity, and instructional value. These findings demonstrate SlideBot’s potential to streamline slide preparation while ensuring accuracy, relevance, and adaptability in higher education.

Yun Wang, Zhaojun Ding, Xuansheng Wu, Siyue Sun, Ninghao Liu, Xiaoming Zhai

Automated scoring plays a crucial role in education by reducing the reliance on human raters and offering scalable and immediate evaluation of student work. While large language models (LLMs) have shown strong potential in this task, their use as end-to-end raters faces challenges such as low accuracy, prompt sensitivity, limited interpretability, and rubric misalignment, which hinder practical implementation. To address the limitations, we propose AutoSCORE, a multi-agent LLM framework enhancing automated scoring via rubric-aligned Structured COmponent REcognition. With two agents, AutoSCORE first extracts rubric-relevant components from student responses and encodes them into a structured representation (i.e., Scoring Rubric Component Extraction Agent), which is then used to assign final scores (i.e., Scoring Agent). This design ensures that model reasoning follows a human-like grading process, enhancing interpretability and robustness. We evaluate AutoSCORE on four benchmark datasets from the ASAP benchmark, using both proprietary and open-source LLMs (GPT-4o, LLaMA-3.1-8B, LLaMA-3.1-70B). Across diverse tasks and rubrics, AutoSCORE predominantly improves scoring accuracy, human-machine agreement (QWK, correlations), and reduces error metrics (MAE, RMSE) compared to single-agent baselines, with particularly strong benefits on complex, multidimensional rubrics, and especially large relative gains on smaller LLMs. These results demonstrate that structured component recognition combined with multi-agent design offers a scalable, reliable, and interpretable solution for automated scoring.

Yingqi Wang, Xiaohang Luo

As generative AI rapidly enters higher education, its cognitive, motivational, and social impacts across disciplines remain underexplored. This qualitative study examines disciplinary epistemologies and digital literacy on AI-assisted academic reading among EFL Chinese students. Guided by Cognitive Load Theory and Self-Determination Theory, participants were 46 university students across Biglan's disciplinary dimensions. We analyzed 46 questionnaires and 32 interviews. Students in soft and applied fields more often report AI reducing intrinsic load, supporting deeper semantic elaboration. In pure and hard fields, students tend to use AI as an interactive tool for questioning, but multi-contextual examples are more likely to introduce extraneous load. By contrast, terminology glossing and decomposition of complex sentences are more often applied in soft and applied fields. Excessive reliance is associated with cognitive offloading and an illusory sense of mastery, shaped by digital literacy and metacognitive awareness. Socially, AI sometimes displaces routine exchanges, but when integrated into group contexts, it facilitates collaboration. The study elaborates applications of CLT and SDT by showing how disciplinary and individual factors shape AI’s cognitive and motivational roles. Practically, it proposes discipline-sensitive design principles and metacognitive prompts, pointing to deployable interventions. Ethical approval and consent were obtained.

Ba-Thinh Tran-Le, Patrick Thomas, Nicholas M. Stiffler, Thuy Ngoc Nguyen

Many AI-based code assistants, particularly those powered by Large Language Models (LLMs), provide complete solutions, which can reduce active problem solving and limit incidental learning, the acquisition of knowledge as a byproduct of task engagement. Such learning requires active participation rather than passive acceptance of AI-generated answers, which might be incorrect. This study examines how incidental learning can be supported through guided interaction. We present LeetCoach, an LLM-assisted coding platform that applies a cognitive forcing strategy, prompting learners to reflect and take incremental steps instead of receiving full solutions. Using LeetCode-style questions, we conducted a pilot study with novice and advanced college programmers who completed tasks under assisted and unassisted conditions. Novices showed substantial post-test gains despite receiving AI guidance only during the intervention, suggesting that incidental exposure improved later performance. Advanced learners showed smaller gains. Across both groups, participants required fewer debugging attempts in the post-test compared to earlier stages, indicating improved debugging efficiency and algorithmic understanding. These findings provide early evidence that LLMs can be designed to promote indirect learning while shaping problem-solving strategies. This work offers a proof of concept for cognitively informed tutoring systems in computer science education and discusses implications for integrating LLMs to enhance both immediate outcomes and lasting skill development.

Van-Khanh Tran, Van-Khai Dang, Duc-Huy Nguyen

While AI can simulate virtual classrooms, effective collaborative learning requires both dynamic interaction and a well-structured pedagogical plan. To address this, we introduce SAGE (Scaffolded Agent-Guided Education), a novel, compositional two-phase framework. First, a planning module automatically generates an optimized pedagogical scenario using a dedicated team of agents. Second, this scenario is used to configure a conversation module, where autonomous agents engage a student in a structured, real-time dialogue. This approach ensures that dynamic, multi-agent interactions are grounded in a pedagogically sound foundation. We evaluate SAGE through simulation and a study with real students. Results show improved performance against a next-speaker prediction baseline (achieving a 72.13% win rate) and demonstrate effective group dynamics. Specifically, our study with students reveals high role adherence from AI agents, a balanced progression between task-oriented and socio-emotional interactions, and a clear scaffolding effect where instructional support fades as learner autonomy increases. Our findings highlight the significant potential of synergizing automated instructional design with autonomous conversational execution for collaborative learning.

Harshil Safi, Megha Bansal, Madhu Vadali, Barbara Bruno, Aditi Kothiyal

Theories of embodied learning emphasize that learning processes are grounded in bodily actions and interactions with the environment, suggesting that movements play a fundamental role in problem solving, decision making, and learning. This perspective holds particular relevance for making-based learning settings, where patterns of movement and spatial engagement can reveal strategic expertise. Prior research has examined distinctions between students who learned and did not learn, but manual coding of actions presents scalability and real-time application challenges. To address this gap, we develop a computer vision–based analysis pipeline for automated detection and characterization of hand movements during complex assembly tasks. In an exploratory study, we apply this approach to video data of students engaged in the assembly of a differential gearbox, quantifying metrics such as amount and speed of movement. Results indicate that learners show fewer right-hand movements than novices and exhibit reduced movement speed, with a progressive decline in speed as the task unfolds. Non-learners, by contrast, display more uneven hand movement speed. These findings, while preliminary, highlight measurable differences in actions of learners and non-learners, and therefore have potential implications for learning support. Specifically, the ability to computationally distinguish movement profiles can inform the design of adaptive learning interventions, providing real-time performance assessment and targeted feedback for making-based learning.

Ryosuke Nakamoto, Brendan Flanagan, Kohei Nakamura, Hiroaki Ogata

Educational assessment requires understanding student problem-solving processes, not just final answers. Current AI-driven analytics focus on static outcomes, missing valuable insights from temporal dynamics. Explain-from-Stroke is a practical framework that captures invisible learning processes by integrating handwriting dynamics with vision-language models. The system extracts temporal features such as writing speed, pauses, and revisions, providing additional context for generating meaningful insights into hidden aspects of student reasoning. Using real classroom data from a Japanese secondary school, the model shows an 18.2% improvement in cognitive depth analysis compared with static approaches. This work provides educators with an accessible method to analyze learning processes using standard tablet technology.

Zachary Nadan, Nathan Goldberg, Roozbeh Aliabadi, Shuhan Li

AI-supported tools have entered K-12 classrooms in recent years to reshape student learning and skill-building. We are particularly interested in AI’s application in literacy subjects, such as English, where students are expected to hone their critical thinking and public speaking skills through AI interactions. This report details the pilot implementation of Debate Guru, an AI-enhanced debate education platform, across two secondary schools with varying instructional contexts. Over the course of a summer school course, educators integrated Debate Guru in one of two ways: 1) by using Debate Guru’s complete curriculum; or 2) by combining platform resources with their own instruction such as a literary text. The pilot was implemented with approximately 50 students across Grade 8-11. Findings suggest significant increases in students’ confidence, argumentative reasoning, and engagement. Teachers reported high usability and strong pedagogical value, while students responded positively to interactive features and AI feedback integration. The pilot demonstrated preliminary usefulness and scalability of AI tutoring systems in debate classes. Future iterations can benefit from longitudinal studies, technical refinements, and school capacity-building to ensure greater generalizability of results and deeper knowledge acquisition.

Yeo Jin Kim, Daeun Hong, Tianshu Wang, Wookhee Min, Snigdha Chaturvedi, Cindy E. Hmelo-Silver, James Lester

In computer-supported collaborative learning environments, analyzing student dialogue is essential for understanding collaborative problem-solving behaviors and supporting effective learning. Prior work often treats all dialogue interactions uniformly, failing to capture how specific dialogue interaction differentially impact learning experiences and outcomes. To address this limitation, we introduce a dialogue-based learning analytics framework that integrates weighted temporal clustering of dialogue with large language model-based interpretation. Our framework identifies student interaction patterns most predictive of group learning gains and uses these insights to enable early prediction of learning outcomes and generate pedagogically meaningful interpretations. We evaluate our framework on collaborative dialogue from middle school students engaged in a collaborative game-based learning environment. Our results show that our framework achieves 83.1% accuracy in learning outcome prediction. In addition, expert evaluations and case studies demonstrate that the identified weighted dialogue patterns reflect key collaborative problem-solving behaviors recognized as important in collaborative learning. By surfacing high-impact interaction patterns and enabling prioritized interpretation generation, our framework provides a promising approach for accurately analyzing students’ collaborative dialogue.

Luyang Fang, Tao Wang, Ping Ma, Xiaoming Zhai

Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled multi-task Mixture-of-Experts (MoE) approach that transfers expertise from multiple task-specific large models (teachers) into a single compact, deployable model (student). The student combines (i) a shared encoder for cross-task representations, (ii) a gated MoE block that balances shared and task-specific processing, and (iii) lightweight task heads. Trained with both ground-truth labels and teacher guidance, the student matches strong task-specific models while being far more efficient to train, store, and deploy. Beyond efficiency, the MoE layer improves transfer and generalization: experts develop reusable skills that boost cross-task performance and enable rapid adaptation to new tasks with minimal additions and tuning. On nine NGSS-aligned science-reasoning tasks (seven for training/evaluation and two held out for adaptation), UniMoE-Guided attains performance comparable to per-task models while using 6x less storage than maintaining separate students, and 87x less than the 20B-parameter teacher. The method offers a practical path toward scalable, reliable, and resource-efficient automated scoring for classroom and large-scale assessment systems.

Jordan Esiason, Priyanka Khare, Claire Aguiar, Dan Carpenter, Wookhee Min, Seung Lee, Gamze Ozogul, Xiaoying Zheng, James Lester

Effective classroom teaching requires instructors to be responsive to their students, such as by pivoting their lectures in real-time to address common misconceptions that their students may have developed. Classroom response systems such as multiple-choice "clicker" systems are one method by which instructors can gauge their students’ understanding during classroom lectures, but open-ended questions that prompt students to engage in self-explanation are better suited to promoting critical thinking. Additionally, analyzing students’ natural language responses typically requires time-consuming manual analysis, which makes it challenging to implement in a classroom setting. To address this challenge, we present an LLM-driven method for automatically assessing students' responses and generating an aggregated summary of LLM-based evaluations for their self-explanations during undergraduate classroom lectures. Our approach extracts relevant knowledge components for a given question, tags students’ responses according to whether they correctly address each knowledge component, and generates class-level summaries that highlight common misconceptions and gaps in knowledge to support instructors in pivoting their lectures in real time. We evaluate the system’s effectiveness at these tagging and summarization tasks on data from an undergraduate computer science course, using quantitative and qualitative metrics such as relevance, sufficiency, hallucination rate, and alignment with instructional goals and desired feedback format gathered through instructor interviews. Results suggest that the explanation-based classroom response system can accurately analyze students’ natural language explanations.

Sandipan Dhar, Srikanth Raj Chetupalli, Preeti Rao

Speaker anonymization aims to modify the speech signal in order to protect the identity of a speaker while preserving the linguistic content. Despite the increasing use of children's voices in educational applications, such as oral reading fluency (ORF) assessment, there is little work on the anonymization aspects. In this work, we investigate the effectiveness of available speaker anonymization methods drawing from traditional speech-production based approaches and a neural codec based method. We investigate the trade-off between privacy protection, measured as the degree of anonymity, and utility preservation, which in the current context of ORF assessment, includes the segmental and suprasegmental features of children’s read speech utterances. We report objective and subjective evaluations using two child-speaker datasets: MPS and SpeechOcean. Our objective evaluation results indicate that the speech-production based method of vocal tract length normalization coupled with pitch-transposition achieves the best balance between privacy and utility. Subjective listening results indicate that naturalness is achievable across methods while the neural method fails to preserve age characteristics, which are more easily controlled by the speech-production driven methods.

Jessica Vandenberg, Alex Goslen, Claire Aguiar, Wookhee Min, Veronica Cateté, Bradford Mott

As large language models (LLMs) and chatbots become increasingly prevalent, there is an urgent need to create engaging, age-appropriate learning activities that foster foundational AI literacy with a focus on natural language processing (NLP). This paper presents the iterative design and implementation of three instructional activities that introduce middle school learners (ages 11--14) to NLP concepts through playful, hands-on experiences aligned with the AI4K12 Big Idea of Natural Interaction. These activities include: (1) an unplugged card game that develops students' understanding of embeddings and similarity, (2) an unplugged collaborative sentence-generation challenge that illustrates how language models work, and (3) a web-based educational game in which students design and interact with chatbots. Each activity was implemented and refined across multiple educational contexts, including teacher professional development workshops, summer camps, and classroom implementations. All activities are designed to be easy to set up, requiring only commonly available classroom technology (e.g., laptops) and a few inexpensive materials (e.g., decks of cards), and are supported with facilitation guides and reflection prompts. Early implementations revealed areas for refinement, leading to clearer scaffolding that helped students connect gameplay to underlying NLP concepts, and post-refinement surveys indicated that students found the activities both enjoyable and educational. Findings suggest that blending unplugged and digital formats enhances comprehension, and that tailoring content to students' local contexts supports engagement. By making these activities openly available, this work contributes to the growing ecosystem of K–12 AI education resources and offers practical guidance for integrating NLP concepts into classroom instruction.

Jessica Vandenberg, Keisha Bailey, Claire Aguiar, Cecilia Xuning Zhang, Danny Schmidt, Treshonda Rutledge, Bradford Mott, Joseph P. Wilson

Introducing AI concepts in the earliest years of schooling can help children make sense of intelligent technologies, yet few resources exist for K–2 classrooms. This paper presents the design and outcomes of a professional development (PD) program supporting K–2 teachers as they explored AI literacy and co-designed unplugged classroom activities. Grounded in AI4K12's Five Big Ideas in AI framework, the PD combined hands-on learning, collaborative design, and micro-teaching opportunities. Guiding activities included Train the AI (pattern recognition), What Happens Next? (consequences of AI use), Who Did the Robot Hear? (data diversity), and Teach the Robot (model training). Educators then created screen-free, English Language Arts-aligned activities using storytelling, sorting, and embodied play to introduce AI topics such as machine learning and fairness in age-appropriate ways. The PD emphasized integrating AI into existing K–2 literacy routines, lowering implementation barriers while supporting vocabulary development, reasoning, and empathy. Teacher reflections revealed growing confidence in adapting AI topics for young learners and highlighted the value of peer collaboration, clear language, and tactile materials.

Sandra Roach, Karis Boyd-Sinkler, Visrut Sudhakar, Shaundra Daily, Miroslav Pajic, Whitney McCoy

As artificial intelligence (AI) becomes increasingly prevalent in society, there is a critical need for accessible K-12 educational resources that introduce students to AI and robotics concepts through engaging, hands-on experiences. In this paper, we present a scalable workshop framework that uses narrative-driven problem solving to teach fundamental AI and autonomous systems concepts to students in grades 5-12. Developed through a collaboration between AI researchers and education specialists, Bot Blitz employs Sphero RVR+ robots within immersive storylines ranging from fairground rescue missions for younger students to urban traffic management scenarios for high schoolers. Preliminary observations from workshops with 56 students show high engagement levels and successful completion of programming challenges.