ECNUClaw: A Learner-Profiled Intelligent Study Companion Framework for K-12 Personalized Education

2026-05-08

AI Summary

This study addresses K-12 education by proposing a personalized intelligent tutoring approach grounded in multidimensional learner profiling. It constructs comprehensive learner profiles encompassing five dimensions—cognition, behavior, affect, metacognition, and context—and dynamically updates these profiles through real-time analysis of student interactions with an intelligent learning companion. The system leverages an adaptive strategy engine to modulate tutoring intensity, encouragement frequency, and Bloom’s taxonomy-based scaffolding. Integrating Chinese educational technology theories, the work adopts Zhang’s three-layer digital profiling framework and an educational brain model to design ECNUClaw, an open-source intelligent tutoring framework featuring a unified OpenAI-compatible layer that supports seven Chinese large language models. This architecture enables real-time, human-AI collaborative profile updating and personalized intervention, with all code publicly released.

Abstract

We introduce ECNUClaw, an open-source framework for building learner-profiled intelligent study companions in K-12 education. The system constructs and maintains a five-dimension learner profile -- covering cognitive, behavioral, emotional, metacognitive, and contextual dimensions -- by extracting signals from student-companion dialogues at each turn. Profile updates feed directly into an adaptive strategy engine that adjusts the companion's guidance intensity, encouragement frequency, and Bloom's taxonomy scaffolding in real time. The framework design draws on three theoretical strands from the Chinese educational technology literature: Zhang's Digital Portrait Three-Layer Framework for learner assessment, the Education Brain model for educational system architecture, and the Human-AI Collaborative IQ concept for companion design philosophy. ECNUClaw is implemented in Python and supports seven Chinese LLM providers through a unified OpenAI-compatible adapter layer. We describe the system architecture, the profiling and adaptation mechanisms, and discuss limitations and next steps. The source code is available at https://github.com/bushushu2333/ECNUClaw.

Problem

• personalized education
• learner profiling
• intelligent study companion
• K-12 education
• adaptive learning

Innovation

• learner profiling
• adaptive strategy engine
• K-12 personalized education
• human-AI collaborative IQ
• multidimensional student modeling