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

2025/09/14 by Yang, Yuheng, Jiang, Wenjia, Wang, Yang +2 · 3 citations
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Multiagent Systems (cs.MA)

paper · doi:10.48550/arxiv.2509.11062

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.

Citations

• Learning to Be A Doctor: Searching for Effective Medical Agent Architectures
• StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements
• Reducing Hallucinations in Vision-Language Models via Latent Space Steering
• Interactive AI Alignment: Specification, Process, and Evaluation Alignment
• The Rise and Potential of Large Language Model Based Agents: A Survey
• AIKernel Semantic DSL Compiler and Deterministic Agent Execution Architecture
• ChatDev: Communicative Agents for Software Development
• Generative Agents: Interactive Simulacra of Human Behavior
• GPT-4 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Affective Coherence Monitoring for Transformer-Based Language Models
• Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
• PaLM: Scaling Language Modeling with Pathways
• Training language models to follow instructions with human feedback
• Learning to summarize from human feedback
• Language Models are Few-Shot Learners
• Scaling Laws for Neural Language Models
• Attention Is All You Need
• Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs
• Cognitive Load During Problem Solving: Effects on Learning
• The Measurement of Observer Agreement for Categorical Data
• A Coefficient of Agreement for Nominal Scales
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Cited by

• PPTArena: A Benchmark for PowerPoint Editing
• Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation
• VideoAgent: Personalized Synthesis of Scientific Videos

Related

• SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations
• SlideSpawn: An Automatic Slides Generation System for Research Publications
• SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation
• Talk to Your Slides: Language-Driven Agents for Efficient Slide Editing
• Awaking the Slides: A Tuning-free and Knowledge-regulated AI Tutoring System via Language Model Coordination