MAS-KCL: Knowledge component graph structure learning with large language model-based agentic workflow

TL;DR

This paper introduces MAS-KCL, a multi-agent system utilizing large language models to learn and optimize knowledge component graphs, improving educational insights and personalized learning pathways.

Contribution

The paper presents a novel multi-agent, LLM-driven algorithm for adaptive KC graph structure learning with a feedback mechanism, enhancing accuracy and efficiency.

Findings

Validated on synthetic datasets showing accurate structure learning

Effective on real-world educational datasets for learning path recognition

Improves targeted instructional interventions

Abstract

Knowledge components (KCs) are the fundamental units of knowledge in the field of education. A KC graph illustrates the relationships and dependencies between KCs. An accurate KC graph can assist educators in identifying the root causes of learners' poor performance on specific KCs, thereby enabling targeted instructional interventions. To achieve this, we have developed a KC graph structure learning algorithm, named MAS-KCL, which employs a multi-agent system driven by large language models for adaptive modification and optimization of the KC graph. Additionally, a bidirectional feedback mechanism is integrated into the algorithm, where AI agents leverage this mechanism to assess the value of edges within the KC graph and adjust the distribution of generation probabilities for different edges, thereby accelerating the efficiency of structure learning. We applied the proposed algorithm to 5 synthetic datasets and 4 real-world educational datasets, and experimental results validate its effectiveness in learning path recognition. By accurately identifying learners' learning paths, teachers are able to design more comprehensive learning plans, enabling learners to achieve their educational goals more effectively, thus promoting the sustainable development of education.