arXiv subjects

Kou Murayama

Publications and source records attributed to Kou Murayama.

6 recordsLinked to original sources

arXiv2026

From Prompting to Epistemic Proactivity: Temporal Trajectories of Student-AI Interaction in Mathematics Learning

GenAI is increasingly used by students as learning companions, yet little is known about how they use these tools in open-ended learning settings, where the goal is not to complete a specific task but to improve understanding and making progress. This study examined Grade-9 students' dialogue with a general-purpose LLM during mathematics practice, in which students prepared a curriculum-aligned skill for a later assessment. We investigated whether students' interactions revealed forms of epistemically proactive AI use: trajectories in which they strategically use and regulate AI to advance their understanding, and whether these trajectories predicted immediate AI-free performance on the same skill. A total of 112 students worked with a web-based LLM tutor on a mathematical-modeling task; 97 completed both AI-free pre- and post-tests. Student turns were coded for self-regulated learning functions, help-seeking content, and mathematical-modeling activity; three dimensions hypothesized to capture epistemically proactive AI use in this task. Descriptively, students' interactions showed little explicit regulation and mostly involved procedural or conceptual questions. Static summaries of AI use, including whole-session prompt functions, request types, modeling stages, and behavioral diversity, did not predict post-test performance after controlling for prior knowledge. In contrast, temporal indicators were informative: students performed better when their interactions shifted from early to late phases toward a more epistemically proactive balance of conceptual or procedural help-seeking and mathematical work, rather than verification, answer-seeking, or validation. These findings suggest that productive AI-supported learning is better understood as a domain-specific trajectory of epistemic proactivity. We discuss implications for AI tutor design and classroom orchestration.

cs.CY↗

arXiv2026

Regulating the AI Tutor: Intentions, Help-Seeking, and Self-Regulated Learning in Adolescent GenAI Use

Generative AI (GenAI) tools are now common learning companions for adolescents, yet how they regulate their use during authentic learning tasks remains poorly understood. Self-regulated learning (SRL) and high-level help-seeking (HS) are commonly proposed as safeguards against passive or shortcut-oriented use, but most empirical studies focus on aggregate learning outcomes rather than these moment-to-moment processes during AI-supported learning. This work-in-progress examines open-ended conversational data from 98 Grade-9 students across three German Gymnasium schools, who used a web-based Mistral-Large tutor to prepare a curriculum-aligned mathematics skill before an exam. Alongside chat logs (1,616 turns; 808 student turns), we collected pre-post domain knowledge, pre-chat learning needs, and self-reported cognitive load. We propose a turn-level codebook combining theory-driven SRL and HS constructs with two LLM-specific inductive codes (agency over the AI; epistemic vigilance), and report preliminary AI-coded results. Although students overwhelmingly selected scaffolded support before the chat, their interactions were dominated by instrumental requests with almost no explicit monitoring or evaluation. Post-test performance was significantly lower than pre-test, and higher extraneous cognitive load predicted lower post-test scores after controlling for prior knowledge. We discuss how these patterns can support hybrid human-AI analysis of interaction patterns and inform scaffolds for more agentic and epistemically proactive GenAI use.

cs.CY↗

arXiv2026

The Future of Feedback: How Can AI Help Transform Feedback to Be More Engaging, Effective, and Scalable?

With digital learning environments becoming more prevalent, the ease with which generative AI enables the scalable production of real-time, automated feedback holds the potential to reshape learning and teaching experiences. This meeting report synthesizes the interdisciplinary perspectives of 50 scholars from educational psychology, computer science, science education, and the learning sciences on the use of generative AI for feedback and its promises and risks in educational practice. We highlight points of convergence in the scholarship, identify areas of debate and unresolved challenges, and outline open questions and future directions for research and educational practice that emerged from structured small-group activities designed to bridge disciplinary barriers.

cs.CY↗

arXiv2026

Protecting and Promoting Human Agency in Education in the Age of Artificial Intelligence

Human agency is crucial in education and increasingly challenged by the use of generative AI. This meeting report synthesizes interdisciplinary insights and conceptualizes four aspects that delineate human agency: human oversight, AI-human complementarity, AI competencies, and relational emergence. We explore practical dilemmas for protecting and promoting agency, focusing on normative constraints, transparency, and cognitive offloading, and highlight key tensions and implications to inform ethical and effective AI integration in education.

cs.HC↗

arXiv2025

Persistent Homology of Topic Networks for the Prediction of Reader Curiosity

Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein's Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text's semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants (n = 49) as they read S. Collins's ''The Hunger Games'' novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73% vs. 30% explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement.

cs.CL↗

arXiv2025

The Illusion of Understanding: How Middle-Schoolers Fail to Regulate Inquiry with ChatGPT in a Science Task

Generative AI (GenAI) tools allow for effortless task completion, potentially fostering cognitive and metacognitive laziness in students. While surveys indicate widespread GenAI use among students as young as 11, their interactions strategies remain under-explored. A critical indicator of these interactions' quality is the ability to lead Question-Asking (QA) cycles: initiating goal-oriented inquiries, critically evaluating AI responses, and regulating subsequent strategies. While these behaviors predict robust learning in traditional settings, their role in AI-mediated environments remains unclear. Addressing this gap, this study investigates middle school students' (N=63, aged 14--15) capacity to adopt these behaviors with GenAI during science investigation tasks. We analyzed their proficiency in distinguishing efficient goal-oriented prompt from inefficient ones, their critical evaluation of AI responses, and their ability to generate follow-up questions to regulate learning in alignment with their informational needs. Findings reveal a pattern of over-reliance: students struggled to discriminate between prompt types, failed to detect vague AI explanations, and frequently terminated inquiry prematurely, without follow-up. Consequently, task performance remained moderate despite unrestricted AI access and high self-reported prior knowledge. Notably, positive AI attitudes were negatively associated with interaction quality, suggesting a disconnect between perceived and actual competence, whereas higher metacognitive skills predicted superior sensitivity to prompt quality. These results underscore the necessity for AI literacy interventions that move beyond technical understanding to explicitly train metacognitive regulation strategies, required for meaningful and sustainable QA-based learning with GenAI.

cs.CY↗