FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets

TL;DR

FACET is a multi-agent LLM framework that personalizes educational worksheets by integrating cognitive and motivational learner profiles, aiming to support teachers in heterogeneous classrooms.

Contribution

This paper introduces a novel multi-agent LLM-based system that generates personalized educational materials considering diverse learner profiles and pedagogical principles.

Findings

High stability and alignment of generated materials with learner profiles

Positive teacher feedback on task structure and suitability

Feasibility demonstrated through automated quality assessment and teacher feedback

Abstract

The increasing heterogeneity of student populations poses significant challenges for teachers, particularly in mathematics education, where cognitive, motivational, and emotional differences strongly influence learning outcomes. While AI-driven personalization tools have emerged, most remain performance-focused, offering limited support for teachers and neglecting broader pedagogical needs. This paper presents the FACET framework, a teacher-facing, large language model (LLM)-based multi-agent system designed to generate individualized classroom materials that integrate both cognitive and motivational dimensions of learner profiles. The framework comprises three specialized agents: (1) learner agents that simulate diverse profiles incorporating topic proficiency and intrinsic motivation, (2) a teacher agent that adapts instructional content according to didactical principles, and (3) an evaluator agent that provides automated quality assurance. We tested the system using authentic grade 8 mathematics curriculum content and evaluated its feasibility through a) automated agent-based assessment of output quality and b) exploratory feedback from K-12 in-service teachers. Results from ten internal evaluations highlighted high stability and alignment between generated materials and learner profiles, and teacher feedback particularly highlighted structure and suitability of tasks. The findings demonstrate the potential of multi-agent LLM architectures to provide scalable, context-aware personalization in heterogeneous classroom settings, and outline directions for extending the framework to richer learner profiles and real-world classroom trials.