Auto-Slides

[ICME 2026] Official implementation of Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations.

Same-category comparison
Name	Rank	Metrics
Tencent/CognitiveKernel-Pro	17,563	Language: Python Stars: 533 Forks: 57 Description: Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414.
sopaco/saga-reader	17,574	Language: Rust Stars: 533 Forks: 30 Description: 💪🏻 Blazing-Fast and Extremely-Lightweight Internet Reader driven by AI. Your AI-Powered think tank assistant.(. Built with Rust, Tauri & Svelte).
ARCANGEL0/EVA	17,577	Language: Python Stars: 532 Forks: 117 Description: EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.
Weixin-Liang/LLM-scientific-feedback	17,584	Language: Python Stars: 532 Forks: 52 Description: Can large language models provide useful feedback on research papers. A large-scale empirical analysis.
archlizheng/frontend-slides-editable	17,586	Language: HTML Stars: 532 Forks: 52 Description: Editable HTML presentation skill for Codex/Claude Code with drag-resize editing, slide reordering, local save/export, and PPTX-to-web conversion. Shout out to @zarazhangrui.
gitanat/simple-ocr-opencv	17,590	Language: Python Stars: 532 Forks: 178 Description: A simple python OCR engine using opencv.
greyovo/PicQuery	17,591	Language: Dart Stars: 532 Forks: 63 Description: 🔍 Search local images with natural language on-device, powered by Apple's MobileCLIP2.
longy2k/obsidian-bmo-chatbot	17,593	Language: TypeScript Stars: 532 Forks: 69 Description: Generate and brainstorm ideas while creating your notes using Large Language Models (LLMs) from Ollama, LM Studio, Anthropic, Google Gemini, Mistral AI, OpenAI, and more for Obsidian.

Key parameters and specifications
Parameter	Value
Language	Python
Category	Applications
Subcategory	Content creation, Research & knowledge
Keywords	Agent society, Document understanding, Multimodal, Unstructured data extraction
Stars	532
Forks	60
Contributors	1
Created date	2025-05-27
Updated date	2026-10-14
Stars in 1 day	0
Stars in 7 days	2
Rank	17,585
Previous rank	6,992
Rank change	-10,593
7-day stars rank	8,872
Previous 7-day stars rank	8,923
7-day stars rank change	51
Total stars rank	18,440
Previous total stars rank	18,405
Total stars rank change	-35

Auto-Slides: Automatic Academic Presentation Generation with Multi-Agent Collaboration

Yuheng Yang1
&nbsp;&nbsp;
Wenjia Jiang1
&nbsp;&nbsp;
Yang Wang1
&nbsp;&nbsp;
Yiwei Wang2
&nbsp;&nbsp;
Chi Zhang1†
  

1AGI Lab, Westlake University&nbsp;
2University of California at Merced
  

†Corresponding author
  

[yangyuheng@westlake.edu.cn](mailto:yangyuheng@westlake.edu.cn)
  

[![](https://img.shields.io/badge/ArXiv-2509.11062-red)](https://arxiv.org/abs/2509.11062)&nbsp;
[![](https://img.shields.io/badge/ICME-2026%20Accepted-brightgreen)](https://2026.ieeeicme.org/)&nbsp;
[![](https://img.shields.io/badge/Project-Page-green)](https://auto-slides.github.io/)&nbsp;
[![](https://img.shields.io/badge/GitHub-Auto--Slides-blue)](https://github.com/wzsyyh/Auto-Slides)&nbsp;
  

 ![](static/figures/teaser.png)

Auto-Slides is an intelligent system that automatically converts academic research papers into well-structured, pedagogically optimized presentation slides. Built on large language models and cognitive science principles, it creates multimodal presentations with interactive customization capabilities.

🏗️ System Architecture

🚀 Features

Intelligent PDF Processing: Automatically extracts text, figures, tables, and structure from research papers using advanced OCR and layout analysis
Multi-Agent Framework: Employs specialized agents for content extraction, presentation planning, verification, and repair
Interactive Customization: Supports real-time refinement through natural language dialogue
Pedagogical Optimization: Creates presentation-oriented narratives that enhance learning and comprehension
Multimodal Output: Generates slides with proper figure placement, table formatting, and code syntax highlighting
Multiple Themes: Supports various Beamer themes (Madrid, Berlin, Singapore, etc.)
Bilingual Support: Works with both English and Chinese papers
Speech Generation: Optional accompanying speech script generation

📋 Requirements

Python 3.8+
LaTeX environment (TeX Live or MiKTeX)
OpenAI API key
8GB+ RAM (for marker-pdf model)

🛠️ Installation

1. Clone the Repository

git clone https://github.com/your-username/auto-slides.git
cd auto-slides

2. Create Virtual Environment (Recommended)

python -m venv venv
source venv/bin/activate  # Linux/Mac
# or
venv\Scripts\activate  # Windows

3. Install Dependencies

pip install -r requirements.txt

4. Download Required Models

Important: Download the marker-pdf model for PDF processing:

python down_model.py

This will download the marker-pdf model to the models/ directory (~2GB).

5. Configure API Keys

Option 1: Use the provided template (Recommended)

Rename the provided template file and add your API key:

# Rename the template file
mv ".env copy" .env

# Edit the .env file and add your OpenAI API key
nano .env  # or use your preferred editor

Option 2: Create from scratch

Create a .env file in the project root:

# OpenAI API Configuration (Required)
OPENAI_API_KEY=your_openai_api_key_here

# Optional: LangSmith for monitoring (uncomment if needed)
# LANGCHAIN_TRACING_V2="true"
# LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
# LANGCHAIN_API_KEY="your_langsmith_api_key_here"
# LANGCHAIN_PROJECT="auto-slides"

Note: The .env copy file contains a template with all available configuration options. Simply rename it to .env and update the OPENAI_API_KEY value with your actual API key.

🎯 Quick Start

Basic Usage

Convert a research paper to presentation slides:

python main.py path/to/your/paper.pdf

Advanced Options

python main.py path/to/your/paper.pdf \
    --language en \
    --model gpt-4o \
    --theme Madrid \
    --output-dir output \
    --verbose

Disable Interactive Revision

By default, Auto-Slides enables interactive revision after generating slides. To disable this feature:

python main.py path/to/your/paper.pdf --no-interactive-revise

Revision Mode

Modify existing presentations with feedback:

python main.py --revise \
    --original-plan=path/to/plan.json \
    --previous-tex=path/to/output.tex \
    --feedback="Please make the title more prominent"

📖 Command Line Options

Required Arguments

pdf_path: Path to the input PDF file

Optional Arguments

Basic Options

--output-dir, -o: Output directory (default: output)
--language, -l: Output language (zh or en, default: en)
--model, -m: Language model to use (default: gpt-4o)
--theme: Beamer theme (default: Madrid)
--verbose, -v: Show verbose logs

Processing Options

--disable-llm-enhancement: Use basic PDF parsing only
--skip-compilation, -s: Generate TEX only, skip PDF compilation
--max-retries, -r: Maximum retries for compilation (default: 5)

Interactive Features

--interactive, -i: Enable interactive mode for presentation plan optimization
--no-interactive-revise: Disable interactive revision after slide generation (enabled by default)

Verification & Repair

--enable-verification: Enable content verification (default: enabled)
--enable-auto-repair: Enable automatic content repair (default: enabled)
--disable-verification: Disable verification and repair (fast mode)

Speech Generation

--enable-speech: Generate accompanying speech script
--speech-duration: Target speech duration in minutes (default: 15)
--speech-style: Speech style (academic_conference, classroom, industry_presentation, public_talk)

Revision Mode

--revise, -R: Enable revision mode
--original-plan: Path to original presentation plan JSON
--previous-tex: Path to previous TEX file
--feedback: User feedback for modifications

📁 Output Structure

The system generates organized output in the specified directory:

output/
├── raw//          # Extracted PDF content
├── plan//         # Presentation plans (JSON)
├── tex//          # Generated LaTeX files and PDFs
├── images//       # Extracted figures and tables
├── verification// # Verification reports
├── repair//       # Auto-repair results
└── speech//       # Generated speech scripts

🔧 System Architecture

Auto-Slides employs a sophisticated multi-agent framework with the following components:

PDF Parser: Extracts content using marker-pdf and OCR technologies
Presentation Planner: Generates structured presentation plans based on cognitive science principles
Verification Agent: Ensures content coverage and accuracy through automated validation
Repair Agent: Automatically fixes identified issues and improves content completeness
TEX Generator: Creates high-quality LaTeX Beamer code with proper formatting
Interactive Editor: Enables real-time customization through natural language dialogue

The system processes research papers through multiple stages, from initial content extraction to final presentation generation, with built-in quality assurance and user interaction capabilities.

🎨 Supported Themes

Madrid (default)
Berlin
Singapore
Warsaw
Copenhagen
And more Beamer themes

🌍 Language Support

English: Full support with optimized prompts
Chinese: Full support with Chinese-specific processing

⚠️ Troubleshooting

Common Issues

Q: Images not extracted or missing?

Ensure the marker-pdf model is downloaded: python down_model.py
Check that images exist in output/images//

Q: API key not working?

Verify OPENAI_API_KEY is set in your .env file
Check your OpenAI account has sufficient credits

Q: LaTeX compilation fails?

Ensure LaTeX is installed and pdflatex is in your PATH
The system automatically uses -shell-escape for code highlighting

Q: Memory issues with large PDFs?

The marker-pdf model requires ~8GB RAM
Consider using --disable-llm-enhancement for basic processing

Performance Tips

Use --disable-verification for faster processing
Enable --skip-compilation to generate TEX only
Use --no-interactive-revise to skip interactive features

📚 Citation

If you use Auto-Slides in your research, please cite our paper:

@article{yang2025autoslides,
  title={Auto-Slides: Automatic Academic Presentation Generation with Multi-Agent Collaboration},
  author={Yang, Yuheng and Jiang, Wenjia and Wang, Yang and Wang, Yiwei and Zhang, Chi},
  journal={arXiv preprint arXiv:2509.11062},
  year={2025},
  note={AGI Lab, Westlake University; University of California at Merced; Corresponding author: Chi Zhang},
  url={https://auto-slides.github.io/},
  eprint={2509.11062},
  archivePrefix={arXiv},
  primaryClass={cs.AI}
}

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📞 Contact

Project Page: auto-slides.github.io
Paper: arXiv:2509.11062
Issues: GitHub Issues
Email: yangyuheng@westlake.edu.cn

🙏 Acknowledgments

marker-pdf for PDF processing
OpenAI for language models
LangChain for LLM orchestration
Beamer for presentation framework

How many stars and forks are recorded?

What is the repository rank?

What language and category are recorded?

Which repository is closest in rank?

🏗️ System Architecture

🚀 Features

📋 Requirements

🛠️ Installation

1. Clone the Repository

2. Create Virtual Environment (Recommended)

3. Install Dependencies

4. Download Required Models

5. Configure API Keys

🎯 Quick Start

Basic Usage

Advanced Options

Disable Interactive Revision

Revision Mode

📖 Command Line Options

Required Arguments

Optional Arguments

Basic Options

Processing Options

Interactive Features

Verification & Repair

Speech Generation

Revision Mode

📁 Output Structure

🔧 System Architecture

🎨 Supported Themes

🌍 Language Support

⚠️ Troubleshooting

Common Issues

Performance Tips

📚 Citation

📄 License

🤝 Contributing

📞 Contact

🙏 Acknowledgments