Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation

2025-11-24

AI Summary

Educators frequently face the labor-intensive challenge of manually adapting presentation slides to align with their pedagogical style and students’ diverse backgrounds. Method: This paper proposes a context-aware, multi-agent slide adaptation framework that systematically identifies slide adaptation challenges through in-depth educator interviews. Integrating natural language processing and intent understanding techniques, it enables end-to-end, high-level instruction-driven automation—encompassing content restructuring, logical refinement, and visual layout optimization. Crucially, AI agents are conceptualized as executors of routine instructional design tasks, establishing a novel human-AI collaborative paradigm. Results: Evaluated on eight real-world courses and 16 revision requests, the framework achieves near-expert performance in intent alignment, content coherence, and factual accuracy (F1 = 0.89), while maintaining high efficiency and visual readability.

Technology Category

• Multiagent Systems: Adversarial Agents
• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The adaptation of teaching slides to instructors' situated teaching needs, including pedagogical styles and their students' context, is a critical yet time-consuming task for educators. Through a series of educator interviews, we first identify and systematically categorize the key friction points that impede this adaptation process. Grounded in these findings, we introduce a novel multi-agent framework designed to automate slide adaptation based on high-level instructor specifications. An evaluation involving 16 modification requests across 8 real-world courses validates our approach. The framework's output consistently achieved high scores in intent alignment, content coherence and factual accuracy, and performed on par with baseline methods regarding visual clarity, while also demonstrating appropriate timeliness and a high operational agreement with human experts, achieving an F1 score of 0.89. This work heralds a new paradigm where AI agents handle the logistical burdens of instructional design, liberating educators to focus on the creative and strategic aspects of teaching.

Problem

• Automating slide adaptation for instructors' pedagogical styles and student contexts
• Addressing time-consuming friction points in teaching slide modification
• Reducing logistical burdens of instructional design through AI agents

Innovation

• Multi-agent framework automates teaching slide adaptation
• Uses high-level instructor specifications for customization
• Validated through real-world courses achieving high performance