PosterGen: Aesthetic-Aware Paper-to-Poster Generation via
Multi-Agent LLMs

Zhilin Zhang^{1,2 ★}  Xiang Zhang^{3 ★}  Jiaqi Wei⁴  Yiwei Xu⁵  Chenyu You¹

¹ Stony Brook University    ² New York University    ³ University of British Columbia   
⁴ Zhejiang University    ⁵ University of California, Los Angeles    ^★ Equal Contribution

In this work, we propose a new multi-agent LLMs framework that is guided by design principles.
Our multi-agent LLMs adopt a workflow of specialist agents that mirrors a professional design process:

• Parser Agent – extracts and structures all content from the source paper.
• Curator Agent – designs a narrative-based storyboard.
• Layout Agent – transforms the storyboard into a spatially balanced, three-column layout.
• Styling Agents – apply a harmonious color palette and a hierarchical typographic system to ensure aesthetic coherence.

This methodology is designed to generate a well-designed poster that minimizes the need for manual fine-tuning.

• 2025.08.26 Our paper is now available on arXiv! 📄
• 2025.08.23 Code Released. PosterGen now available! 🎉

• Operating System: Windows, Linux, or macOS
• Python Version: 3.11

# Create and activate conda environment
conda create -n poster python=3.11 -y
conda activate poster
pip install -r requirements.txt

git clone -b main https://github.com/Y-Research-SBU/PosterGen.git
cd PosterGen

Windows:

1. Download and install LibreOffice from official website
2. Add LibreOffice to your system PATH:
   • Default installation: Add C:\Program Files\LibreOffice\program to PATH
   • Or custom installation: Add <your_install_path>\LibreOffice\program to PATH

macOS:

brew install --cask libreoffice

Ubuntu/Linux:

sudo apt install libreoffice
# Or using snap:
sudo snap install libreoffice

Create a .env file in the project root with your API keys:

OPENAI_API_KEY="your_openai_key"
ANTHROPIC_API_KEY="your_anthropic_key"

Before running the multi-agent pipeline, organize your files in the data/ folder:

data/
└── <your_paper_name>/
    ├── paper.pdf          # Your research paper (required)
    ├── aff.png           # Affiliation logo for color extraction (required)
    └── logo.png          # Conference logo for poster (required)

Examples (check data/ folder):

data/
└── Neural_Encoding_and_Decoding_at_Scale/
    ├── paper.pdf
    ├── aff.png
    └── logo.png
└── ...

Generate your poster with a single command:

python -m src.workflow.pipeline \
  --poster_width 54 --poster_height 36 \
  --paper_path ./data/Your_Paper_Name/paper.pdf \
  --text_model gpt-4.1-2025-04-14 \
  --vision_model gpt-4.1-2025-04-14 \
  --logo ./data/Your_Paper_Name/logo.png \
  --aff_logo ./data/Your_Paper_Name/aff.png

Parameters:

• --poster_width/height: Poster dimensions in inches, with aspect ratio (w/h): lower bound 1.4 (ISO A paper size), upper bound 2 (human vision limit)
• --paper_path: Path to your PDF paper
• --text_model: LLM for text processing (options: "gpt-4.1-2025-04-14" (default), "gpt-4o-2024-08-06", "gpt-4.1-mini-2025-04-14", "claude-sonnet-4-20250514")
• --vision_model: Vision model for analysis (same options as text_model)
• --logo: Your institution/lab logo
• --aff_logo: Affiliation logo (used for color scheme extraction)

Developed by: React + TypeScript + Vite

Upload your PDF paper and logos through drag-and-drop, configure models and dimensions, then generate and download your poster files.

Prerequisites:

• Node.js installed
• Main PosterGen dependencies installed (pip install -r requirements.txt from project root)
• API keys configured in .env file

# Install main project dependencies (if not done already)
pip install -r requirements.txt

# Start backend
cd webui && pip install -r requirements.txt && python start_backend.py

# Start frontend (in new terminal, from project root)
cd webui && sh ./start_frontend.sh

# Open http://localhost:3000 in your browser

After successful generation, you'll find your results in the output/ folder:

output/
└── <paper_name>/
    ├── <paper_name>.png           # final poster image
    ├── <paper_name>.pptx          # editable PowerPoint file
    ├── assets/                    # extracted content from paper via Marker
    │   ├── figures.json           # figure metadata with aspect ratios
    │   ├── tables.json            # table metadata with aspect ratios
    │   ├── figure-*.png           # individual figures from paper
    │   ├── table-*.png            # individual tables from paper
    │   └── fig_tab_caption_mapping.json  # caption mappings
    └── content/                   # multi-agent artifacts
        ├── raw.md                         # raw text extraction
        ├── structured_sections.json      # organized sections
        ├── classified_visuals.json       # categorized visuals
        ├── narrative_content.json        # paper summary
        ├── story_board.json              # content organization
        ├── initial_layout_data.json      # initial layout
        ├── column_analysis.json          # column usage stats
        ├── optimized_story_board.json    # balanced content
        ├── balancer_decisions.json       # optimization details
        ├── final_column_analysis.json    # final usage metrics
        ├── optimized_layout.json         # balanced layout
        ├── final_design_layout.json      # element coordinates
        ├── color_scheme.json             # color palette
        ├── section_title_design.json     # title styling
        ├── keywords.json                  # highlighted terms
        ├── styled_layout.json            # formatted text
        └── styling_interfaces.json       # typography settings

Our system uses 6 specialized AI agents working together:

1. Parser Agent: Extracts and structures content from paper PDF
2. Curator Agent: Plans content organization and visual placement
3. Layout Agent: Calculates precise positioning and spacing
   • Balancer Sub-Agent: Optimizes column utilization and prevents overflow
4. Color Agent: Generates cohesive color schemes from your affiliation logo
5. Font Agent: Applies typography and keyword highlighting
6. Renderer: Generates final PowerPoint and image files

• Professional Layout: CSS-like precision positioning with proper spacing
• Intelligent Balancing: Automatic column optimization prevents overflow
• Color Harmony: Automatic color scheme generation from your institution branding
• Typography Excellence: Professional font choices and keyword highlighting
• Flexible Output: Both PNG images and editable PowerPoint files
• Academic Standards: Follows poster design best practices for conferences

The system supports customization through config/poster_config.yaml. You can adjust:

• Layout parameters (margins, padding, spacing)
• Typography settings (fonts, sizes, line spacing)
• Color generation algorithms
• Visual asset sizing constraints
• Content optimization thresholds

Custom Fonts: If you would like to use other fonts, you can add the font files under fonts/, modify the get_font_file_path() mapping in src/layout/text_height_measurement.py, and adjust the 'typography' in config/poster_config.yaml.

Our system generates professional academic posters with high visual quality. Here are some examples of generated posters:

@article{zhang2025postergen,
    title={PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs},
    author={Zhilin Zhang and Xiang Zhang and Jiaqi Wei and Yiwei Xu and Chenyu You},
    journal={arXiv:2508.17188},
    year={2025}
}

This codebase is built upon following open-source projects. We express our sincere gratitude to:

• LangGraph: Multi-agent workflow framework;
• Marker: High-quality PDF parsing library that enables accurate content extraction from research papers.