Research on the Construction of Personalized Teaching Pathways for Generative AI-Driven Intelligent Auditing Curriculum

Abstract

With the rapid advancement of generative artificial intelligence technology, its capabilities for dynamic content generation and contextualized interaction offer new technological pathways to transcend traditional educational paradigms. This study focuses on auditing courses, aiming to explore the construction of a personalized teaching pathway for intelligent courses driven by generative AI. The research begins by explicating the theoretical foundation for the deep integration of generative AI and personalized instruction, drawing upon pedagogical theory, cognitive science, and the specific characteristics of auditing as a discipline. Subsequently, it systematically constructs a framework for generating teaching pathways, centered on dynamic learner modeling, auditing knowledge graphs, and personalized content adaptation, and designs a dynamic pathway planning algorithm based on multi‑objective optimization. Finally, an implementation and optimization system is proposed, encompassing multidimensional efficacy evaluation, feedback‑based refinement mechanisms, and a sustainable evolution logic, to form an intelligent teaching system capable of adapting to learners’ cognitive development and evolving in tandem with the discipline and technology. This provides theoretical reference and technical implementation insights for the reform of teaching in disciplines oriented toward higher‑order competencies, such as auditing.