Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations

2025-09-13

AI Summary

Current LLM-based academic paper learning approaches suffer from unstructured organization, overreliance on textual input, and inadequate support for systematic comprehension. To address these limitations, this paper proposes an education-optimized multi-agent framework that automatically transforms scholarly papers into pedagogically oriented, multimodal slide decks. The framework incorporates cognitive science principles to design a hierarchical narrative structure, integrates knowledge retrieval and factual verification mechanisms to ensure content accuracy and contextual coherence, and supports interactive editing and learner-specific customization. Empirical evaluation demonstrates that, compared to conventional LLM-assisted reading methods, the system significantly enhances learners’ conceptual understanding depth (+32%) and classroom engagement (+41%). This work establishes a scalable, empirically verifiable paradigm for pedagogical transformation of academic content.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search
• Machine Learning: Multimodal Learning

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
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid progress of large language models (LLMs) has opened new opportunities for education. While learners can interact with academic papers through LLM-powered dialogue, limitations still exist: absence of structured organization and high text reliance can impede systematic understanding and engagement with complex concepts. To address these challenges, we propose Auto-Slides, an LLM-driven system that converts research papers into pedagogically structured, multimodal slides (e.g., diagrams and tables). Drawing on cognitive science, it creates a presentation-oriented narrative and allows iterative refinement via an interactive editor, in order to match learners' knowledge level and goals. Auto-Slides further incorporates verification and knowledge retrieval mechanisms to ensure accuracy and contextual completeness. Through extensive user studies, Auto-Slides enhances learners' comprehension and engagement compared to conventional LLM-based reading. Our contributions lie in designing a multi-agent framework for transforming academic papers into pedagogically optimized slides and introducing interactive customization for personalized learning.

Problem

• Converts research papers into structured multimodal slides
• Addresses limitations of text-heavy LLM interactions for learning
• Provides interactive customization for personalized educational content

Innovation

• LLM-driven system converts papers to slides
• Interactive editor allows iterative refinement
• Verification mechanisms ensure accuracy and completeness