Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a modular agentic AI chatbot architecture designed for responsible educational assistance, addressing the limitations of monolithic LLMs in adhering to pedagogical principles. The architecture decomposes exercise solving into distinct stages, each handled by specialized modules incorporating targeted pedagogical advice. By modularizing the agent, the system aims to improve controllability, transparency, and oversight in guiding students through the learning process.
Out-of-the-box LLMs left to their own devices might actually *hurt* learning, so this paper breaks down educational assistance into modules that can be steered by pedagogical principles.
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.