Multi-agent large language models promise flexible, modular architectures for delivering personalized educational content. Drawing on a pilot randomized controlled trial with middle school students (n = 23), we introduce a two-agent GPT-4 framework in which a Profiler agent infers learner-specific preferences and a Rewrite agent dynamically adapts science passages via an explicit message-passing protocol. We implement structured system and user prompts as inter-agent communication schemas to enable real-time content adaptation. The results of an ordinal logistic regression analysis hinted that students may be more likely to prefer texts aligned with their profile, demonstrating the feasibility of multi-agent system-driven personalization and highlighting the need for additional work to build upon this pilot study. Beyond empirical validation, we present a modular multi-agent architecture detailing agent roles, communication interfaces, and scalability considerations. We discuss design best practices, ethical safeguards, and pathways for extending this framework to collaborative agent networks—such as feedback-analysis agents—in K-12 settings. These results advance both our theoretical and applied understanding of multi-agent LLM systems for personalized learning.

Engineering education often emphasizes technical competencies while underemphasizing and devaluing the social, ethical, and political contexts of engineering systems. This gap is particularly pronounced in middle-year courses, where students develop technical fluency but rarely confront the sociotechnical complexity of real-world problems. We propose sociotechnical judgment as a framework to help students see the intimately intertwining nature of technical knowledge and social, ethical, and contextual reasoning, using energy systems—particularly offshore wind—as an illustrative domain. We designed three course-integrated case studies in thermodynamics, circuits, and statics/dynamics to embed sociotechnical judgment in middle-year engineering courses. These cases include pedagogical strategies, such as project-based learning, problem-based learning, and role-play exercises connecting technical analysis with social, environmental, and policy considerations. The design of these case studies is rooted in real-world problems surrounding U.S. offshore wind, engineering science learning outcomes, and ABET student outcomes. In these pedagogies, we have created opportunities for students to analyze technical systems while engaging with social, ecological, and political factors. Offshore wind projects, including turbine siting, transmission system design, and efficiency trade-offs, provide opportunities to operationalize sociotechnical reasoning in authentic, regionally relevant contexts. Sociotechnical judgment provides a practical framework for bridging technical competency and contextual reasoning in engineering education. Integrating sociotechnical cases into core courses will prepare students to navigate complex, real-world systems through engagement with ethical, social, and environmental considerations inherent in engineering practice.