# Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance

arXiv: https://arxiv.org/abs/2605.30187 · HTML: https://mlsanity.com/paper/2605.30187/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 10 of 10)

- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Sycophancy in Large Language Models: Causes and Mitigations](https://mlsanity.com/paper/2411.15287/) (2024)
- [Knowledge Tracing: A Survey](https://mlsanity.com/paper/2201.06953/) (2022)
- [Automatic Generation of Socratic Subquestions for Teaching Math Word Problems](https://mlsanity.com/paper/2211.12835/) (2022)
- [On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives](https://mlsanity.com/paper/2404.04059/) (2024)
- [Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)](https://mlsanity.com/paper/2505.21091/) (2025)
- [Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems](https://mlsanity.com/paper/2310.01420/) (2023)
- [From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education](https://mlsanity.com/paper/2509.21972/) (2025)
- [An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide](https://mlsanity.com/paper/2402.14837/) (2024)
- [Scaffolding Metacognition in Programming Education: Understanding Student-AI Interactions and Design Implications](https://mlsanity.com/paper/2511.04144/) (2025)

## Abstract (arXiv)

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.