Synthesis: Instructional Agents is a multi-agent LLM framework that automates end-to-end course material generation by simulating role-based collaboration among Teaching Faculty, Instructional Designer, Teaching Assistant, Course Coordinator, and Program Chair agents, all structured around the ADDIE instructional design framework. Evaluated across 5 university courses, the system supports four modes (Autonomous, Catalog-Guided, Feedback-Guided, Full Co-Pilot) balancing automation and human oversight.
System Design
The framework maps the first three phases of the ADDIE framework (Analyze, Design, Develop) onto a multi-agent workflow:
Analyze: Teaching Faculty + Course Coordinator produce an Instructional Foundation Report (objectives, learner profiles, constraints)Design: Teaching Faculty + Instructional Designer structure syllabi, slide outlines, and assessment plansDevelop: Teaching Assistant generates concrete materials (slides, scripts, assessments); Program Chair reviews from a program-level perspective; Test Student agent supplies simulated learner feedbackThe Teaching Faculty agent serves as the primary authority throughout, maintaining continuous oversight.
Four Interaction Modes
1. Autonomous — fully automated generation with no human input
2. Catalog-Guided — human provides a course catalog description as seed input
3. Feedback-Guided — human reviews and provides iterative feedback between phases
4. Full Co-Pilot — tight human-AI collaboration throughout all phases
Evaluation
Evaluated across 5 university-level courses using both human and automated reviewers. Key findings:
Produces high-quality materials that are reviewed and refined by teaching faculty prior to classroom useSignificantly reduces time required to prepare classroom-ready contentMulti-agent collaboration preserves pedagogical coherence better than single-model approachesTrade-offs exist between automation level and output quality — Feedback-Guided and Full Co-Pilot modes produce higher-quality outputs at the cost of more human involvementSignificance
Scalable instructional design — supports institutions with limited instructional design capacityDemocratizing access — reduces barriers to high-quality course material creation, especially in underserved settingsRole-based coherence — simulates real-world instructional collaboration rather than treating generation as an isolated taskSource code available at the project websiteConnected Concepts
Higher EdLLMConnected Articles
A4l Analytics Pipeline — Generalizing a Highly Configurable Analytics Pipeline to Replicate and Support Educational Research Across Multiple D...Aaai2026 Prompting Literacy K12 — Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy ModuleAcademiclaw Student Agent Benchmark — AcademiClaw: When Students Set Challenges for AI AgentsAdaptive Pretesting Retention — Do Gains from Generative AI-Enabled Adaptive Pretesting Persist? Evidence from a Retention StudyAdhd Video Segmentation Computing Education — Leveling the Playing Field: Temporal Video Segmentation for Individuals with ADHD in Computing EducationAffective Text Wearable Student Health — A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health MonitoringAgency Gap AI Writing — The agency gap in AI-supported writing: how reactive and proactive agent designs shape multimodal reasoningAgent Voice Accents K12 Group Learning — Exploring How Agent Voice Accents Shape Human-AI Collaboration in K-12 Group LearningAgentic AI Education Scoping Review — Agentic AI in Education: A Scoping Review of Research Landscape, Capabilities, and the Frontier Agent ParadigmAgentic Education Coding — Agentic Education with AI Coding AssistantsAgentic Literacy Debt — Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet NamedAgents That Teach Incidental Learning — Agents That Teach: Designing Incidental Learning Back into AI-Assisted Software DevelopmentAgreement Not Quality LLM Coding Verification — Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not G...AI Adult Learning Design — Guidelines for Designing AI Technologies to Support Adult LearningAI Adult Learning Guidelines Dis2026 — Guidelines for Designing AI Technologies to Support Adult LearningAI Agents Constructive Conflict Design Education 2026 — Enacting Constructive Conflicts with AI Agents to Enhance Reconsideration among Novice Interaction DesignersAI Agents Peer Learning Discourse — When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook CommunityAI Assessment Scale Reform — A bit of chaos and madness": The AI Assessment Scale and the work of assessment reformAI Assistance Discretionary Feedback — AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher EducationAI Assisted Learning Modes Eeg — An exploratory behavioral and electroencephalographic study of artificial intelligence-assisted learning modes in hig...AI Assisted Se Curriculum Syllabus Analysis 2026 — Mapping the Emerging Curriculum for AI-Assisted Software Engineering via Syllabus AnalysisAI Assisted Writing Research Teams — Smaller, Younger, and More Impactful: How AI-Assisted Writing Transforms Research TeamsAI Availability Student Motivation — Why Put in This Much Effort?": How AI Availability Shapes Students’ Motivation in Introductory ProgrammingAI Campus Wellbeing Tools — AI-Driven Tools for Enhancing Campus Well-being: Prevention and InterventionAI Changing Teaching Workflows — How AI Is Changing Teaching WorkflowsCitation
Yao, H., Xu, W., Turnau, J., Kellam, N., & Wei, H. (2026). Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design. In Proceedings of EACL 2026.