Hyoungwook Jin

Hyoungwook Jin, Minju Yoo, Jieun Han et al.

Generative AI chatbots enable personalized problem-solving, but effective learning requires students to self-regulate both how they seek help and how they use AI-generated responses. Considering engagement modes across these two actions reveals nuanced reliance patterns: for example, a student may actively engage in help-seeking by clearly specifying areas of need, yet engage passively in response-use by copying AI outputs, or vice versa. However, existing research lacks systematic tools for jointly capturing engagement across help-seeking and response-use, limiting the analysis of such reliance behaviors. We introduce RelianceScope, an analytical framework that characterizes students' reliance on chatbots during problem-solving. RelianceScope (1) operationalizes reliance into nine patterns based on combinations of engagement modes in help-seeking and response-use, and (2) situates these patterns within a knowledge-context lens that accounts for students' prior knowledge and the instructional significance of knowledge components. Rather than prescribing optimal AI use, the framework enables fine-grained analysis of reliance in open-ended student-AI interactions. As an illustrative application, we applied RelianceScope to analyze chat and code-edit logs from 79 college students in a web programming course. Results show that active help-seeking is associated with active response-use, whereas reliance patterns remain similar across knowledge mastery levels. Students often struggled to articulate their knowledge gaps and to adapt AI responses. Using our annotated dataset as a benchmark, we further demonstrate that large language models can reliably detect reliance during help-seeking and response-use. We conclude by discussing the implications of RelianceScope and the design guidelines for AI-supported educational systems.

Hyoungwook Jin, Yoonsu Kim, Dongyun Jung et al.

Mathematics learning entails mastery of both content knowledge and cognitive processing of knowing, applying, and reasoning with it. Automated math assessment primarily has focused on grading students' exhibition of content knowledge by finding textual evidence, such as specific numbers, formulas, and statements. Recent advancements in problem-solving, image recognition, and reasoning capabilities of large language models (LLMs) show promise for nuanced evaluation of students' cognitive skills. Diagnosing cognitive skills needs to infer students' thinking processes beyond textual evidence, which is an underexplored task in LLM-based automated assessment. In this work, we investigate how state-of-the-art LLMs diagnose students' cognitive skills in mathematics. We constructed MathCog, a novel benchmark dataset comprising 639 student responses to 110 expert-curated middle school math problems, each annotated with detailed teachers' diagnoses based on cognitive skill checklists. Using MathCog, we evaluated 16 closed and open LLMs of varying model sizes and vendors. Our evaluation reveals that even the state-of-the-art LLMs struggle with the task, all F1 scores below 0.5, and tend to exhibit strong false confidence for incorrect cases ($r_s=.617$). We also found that model size positively correlates with the diagnosis performance ($r_s=.771$). Finally, we discuss the implications of these findings, the overconfidence issue, and directions for improving automated cognitive skill diagnosis.

Kwon Ko, Hyoungwook Jin

Thirty years ago, Wooldridge and Jennings defined intelligent agents through four properties: autonomy, reactivity, pro-activeness, and social ability. Today, advances in AI can empower everyday objects to become such intelligent agents. We call such objects agentic objects and envision that they can form an agentic society: a collective agentic environment that perceives patterns, makes judgments, and takes actions that no single object could achieve alone. However, individual capability does not guarantee coordination. Through an illustrative scenario of a teenager experiencing bullying and depression, we demonstrate both the promise of coordination and its failure modes: false positives that destroy trust, deadlocks that prevent action, and adversarial corruption that poisons judgment. These failures reveal open questions spanning three phases: what to share, how to judge, and when to act. These questions chart a research agenda for building agentic societies.