Date
Publisher
arXiv
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.
Study at a glance
- Question: Can a multi-agent AI system generate classroom teaching materials effectively adapted to individual learner needs?
- Setting and data: Grade 8 German mathematics curriculum; 4 simulated learner profiles; exploratory review with 5 in-service K-12 teachers in Germany.
- Method: Multi-agent system development, automated LLM-based evaluation across 10 iterations, and qualitative teacher feedback with think-aloud protocols.
Why it matters
Heterogeneous classrooms challenge teachers to differentiate instruction, yet most AI personalization tools focus strictly on student performance rather than motivational needs or direct teacher support.
Key findings
- In automated testing, the multi-agent system reliably created personalized worksheets, earning high marks for task suitability (mean 4.78 out of 6) and clarity (mean 4.76).
- Five German in-service teachers gave high ratings for suitability (mean 5.05 out of 6) and didactical structure (mean 4.95), finding the differentiated tasks valuable.
- Teachers suggested refining materials for less-motivated or struggling learners by incorporating explicit math operators, worked examples, guided hints, and everyday narrative contexts.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Why use AI?
