Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance

2026-05-28

AI Summary

This work addresses the tendency of current large language models in educational applications to overlook fundamental pedagogical principles, which may inadvertently impair students’ transfer learning, critical thinking, and creativity. To mitigate this issue, the paper proposes a modular agent architecture grounded in established educational objectives, decomposing problem-solving into distinct phases and embedding pedagogically informed, stage-specific guidance within each. Departing from conventional monolithic model designs, this approach pioneers a teaching-principle-driven, phased AI tutoring mechanism. The framework not only maintains instructional efficacy but also substantially enhances the controllability, transparency, and supervisability of the tutoring process, thereby advancing the development of more responsible and educationally sound AI-powered learning assistants.

Abstract

The widespread adoption of AI chatbots in education will drastically change learning, making responsible deployment a critical concern. While large language models (LLMs) might have access to sources discussing insights from educational sciences, they are not particularly inclined to adhere to pedagogical concepts, risking negative effects on the learning process, such as a loss of transfer capabilities, critical thinking, or creativity. In this paper, we introduce an agentic AI chatbot architecture assisting students with exercise solving, specifically designed to contribute to more responsible AI use in education. We base our conceptual development on the identification of several desiderata for responsible LLM-based educational systems, argue for the structural shortcomings inherent in monolithic, out-of-the-box solutions, and instead suggest modularizing the agentic architecture. We propose specific modules for different stages of exercise solving, enabling incorporation of targeted pedagogical advice, guiding students through the learning process in a more controllable, transparent, and overseeable manner.

Problem

• educational AI
• responsible AI
• large language models
• pedagogical principles
• learning assistance

Innovation

• modular architecture
• educational LLM
• responsible AI
• pedagogical guidance
• agentic AI