A Closed-Loop Personalized Learning Agent Integrating Neural Cognitive Diagnosis, Bounded-Ability Adaptive Testing, and LLM-Driven Feedback
Zhifeng Wang, Xinyue Zheng, Chunyan Zeng
TL;DR
EduLoop-Agent tackles the fragmentation of personalized learning by unifying fine-grained cognitive diagnosis, adaptive item selection, and grounded feedback within a closed-loop Diagnosis–Recommendation–Feedback framework. It combines Neural Cognitive Diagnosis (NCD) for knowledge-point mastery, a Boundened-Ability CAT (BECAT) policy for informative item selection, and an LLM-based feedback module grounded in model evidence. The approach demonstrates strong predictive performance, improved recommendation relevance, and interpretable, actionable guidance on the ASSISTments dataset, suggesting practical pathways to individualized learning trajectories. The work highlights the importance of integrated pipelines and grounded feedback for scalable, effective intelligent tutoring systems, while noting limitations such as offline evaluation and prompts safety considerations.
Abstract
As information technology advances, education is moving from one-size-fits-all instruction toward personalized learning. However, most methods handle modeling, item selection, and feedback in isolation rather than as a closed loop. This leads to coarse or opaque student models, assumption-bound adaptivity that ignores diagnostic posteriors, and generic, non-actionable feedback. To address these limitations, this paper presents an end-to-end personalized learning agent, EduLoop-Agent, which integrates a Neural Cognitive Diagnosis model (NCD), a Bounded-Ability Estimation Computerized Adaptive Testing strategy (BECAT), and large language models (LLMs). The NCD module provides fine-grained estimates of students' mastery at the knowledge-point level; BECAT dynamically selects subsequent items to maximize relevance and learning efficiency; and LLMs convert diagnostic signals into structured, actionable feedback. Together, these components form a closed-loop framework of ``Diagnosis--Recommendation--Feedback.'' Experiments on the ASSISTments dataset show that the NCD module achieves strong performance on response prediction while yielding interpretable mastery assessments. The adaptive recommendation strategy improves item relevance and personalization, and the LLM-based feedback offers targeted study guidance aligned with identified weaknesses. Overall, the results indicate that the proposed design is effective and practically deployable, providing a feasible pathway to generating individualized learning trajectories in intelligent education.