Co-designing Large Language Model Tools for Project-Based Learning with K12 Educators

2025-02-13

AI Summary

K–12 teachers face persistent challenges in implementing project-based learning (PBL), including complex instructional design, inefficient process management, insufficiently personalized assessment, and imbalanced teacher–student roles. Method: This study introduces a teacher-driven co-design paradigm for LLM-powered educational tools, grounded in iterative cycles of teacher interviews, collaborative design workshops, and wireframe prototyping—integrating educational technology principles and human–AI collaboration theory. Contribution/Results: We developed the first empirically grounded, PBL-specific LLM design guideline that simultaneously supports teacher professional development, embeds ethical guardrails, and ensures classroom feasibility. The study distills four actionable, implementation-oriented design principles for LLM-augmented PBL, specifying mechanisms for resource adaptation, boundaries for ethical AI use, and pathways for sustained pedagogical impact—thereby establishing an evidence-based theoretical framework and practical co-design methodology for AI-enabled educational tool development.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The emergence of generative AI, particularly large language models (LLMs), has opened the door for student-centered and active learning methods like project-based learning (PBL). However, PBL poses practical implementation challenges for educators around project design and management, assessment, and balancing student guidance with student autonomy. The following research documents a co-design process with interdisciplinary K-12 teachers to explore and address the current PBL challenges they face. Through teacher-driven interviews, collaborative workshops, and iterative design of wireframes, we gathered evidence for ways LLMs can support teachers in implementing high-quality PBL pedagogy by automating routine tasks and enhancing personalized learning. Teachers in the study advocated for supporting their professional growth and augmenting their current roles without replacing them. They also identified affordances and challenges around classroom integration, including resource requirements and constraints, ethical concerns, and potential immediate and long-term impacts. Drawing on these, we propose design guidelines for future deployment of LLM tools in PBL.

Problem

• Enhance PBL with LLM tools
• Address K12 educators' PBL challenges
• Automate tasks, personalize learning

Innovation

• Co-designing LLM tools
• Automating routine tasks
• Enhancing personalized learning