Search papers, labs, and topics across Lattice.
The paper introduces ARCHED, a multi-stage framework for AI-assisted instructional design that prioritizes human educator agency and pedagogical rigor. ARCHED uses a cascaded workflow aligned with Bloom's taxonomy, employing specialized AI agents for generating pedagogical options and evaluating alignment with learning objectives. Empirical evaluations demonstrate that ARCHED enhances instructional design quality while preserving educator oversight, addressing limitations of existing automation-focused approaches.
Human educators can now leverage a structured AI framework to enhance instructional design quality without sacrificing oversight, thanks to ARCHED's cascaded workflow and specialized AI agents.
Integrating Large Language Models (LLMs) in educational technology presents unprecedented opportunities to improve instructional design (ID), yet existing approaches often prioritize automation over pedagogical rigor and human agency. This paper introduces ARCHED (AI for Responsible, Collaborative, Human-centered Education Instructional Design), a structured multi-stage framework that ensures human educators remain central in the design process while leveraging AI capabilities. Unlike traditional AI-generated instructional materials that lack transparency, ARCHED employs a cascaded workflow aligned with Bloom's taxonomy. The framework integrates specialized AI agents - one generating diverse pedagogical options and another evaluating alignment with learning objectives - while maintaining educators as primary decision-makers. This approach addresses key limitations in current AI-assisted instructional design, ensuring transparency, pedagogical foundation, and meaningful human agency. Empirical evaluations demonstrate that ARCHED enhances instructional design quality while preserving educator oversight, marking a step forward in responsible AI integration in education.
