FACET: Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets
This addresses the problem of scalable, context-aware personalization for teachers in K-12 education, though it is incremental as it builds on existing AI and multi-agent approaches.
The paper tackled the challenge of personalizing educational materials for heterogeneous student populations in mathematics by developing the FACET framework, a teacher-facing multi-agent LLM system that generated individualized worksheets integrating cognitive and motivational profiles, with results showing high stability and alignment in automated evaluations and positive teacher feedback on task suitability.
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.