Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design

TL;DR

This paper demonstrates that embedding pedagogical frameworks into multi-agent LLM systems enhances the quality and relevance of generated K-12 instructional materials, as perceived by teachers, compared to traditional prompt-based approaches.

Contribution

It introduces a multi-agent system embedding the KLI pedagogical framework to improve AI-generated educational content, moving pedagogical expertise from prompts to system architecture.

Findings

Teachers preferred collaborative MAS-CMD activities for creativity and relevance.

Small differences in rubric scores between systems, often statistically insignificant.

Qualitative feedback favored the collaborative MAS-CMD approach.

Abstract

K-12 educators are increasingly using Large Language Models (LLMs) to create instructional materials. These systems excel at producing fluent, coherent content, but often lack support for high-quality teaching. The reason is twofold: first, commercial LLMs, such as ChatGPT and Gemini which are among the most widely accessible to teachers, do not come preloaded with the depth of pedagogical theory needed to design truly effective activities; second, although sophisticated prompt engineering can bridge this gap, most teachers lack the time or expertise and find it difficult to encode such pedagogical nuance into their requests. This study shifts pedagogical expertise from the user's prompt to the LLM's internal architecture. We embed the well-established Knowledge-Learning-Instruction (KLI) framework into a Multi-Agent System (MAS) to act as a sophisticated instructional designer. We tested three systems for generating secondary Math and Science learning activities: a Single-Agent baseline simulating typical teacher prompts; a role-based MAS where agents work sequentially; and a collaborative MAS-CMD where agents co-construct activities through conquer and merge discussion. The generated materials were evaluated by 20 practicing teachers and a complementary LLM-as-a-judge system using the Quality Matters (QM) K-12 standards. While the rubric scores showed only small, often statistically insignificant differences between the systems, the qualitative feedback from educators painted a clear and compelling picture. Teachers strongly preferred the activities from the collaborative MAS-CMD, describing them as significantly more creative, contextually relevant, and classroom-ready. Our findings show that embedding pedagogical principles into LLM systems offers a scalable path for creating high-quality educational content.