Google Research's PaperOrchestra automates AI research paper generation from raw materials, coordinating specialized agents to handle outlines, literature synthesis, writing, refinement, and plotting.

Google Research has released PaperOrchestra, a multi-agent framework that automates the end-to-end process of writing AI research papers. The system transforms raw materials—research ideas and experimental logs—into submission-ready LaTeX manuscripts, including literature synthesis and generated plots.

How it works

PaperOrchestra coordinates specialized agents for different stages of paper generation. An outline agent structures the paper, a literature review agent synthesizes relevant citations, a section writing agent generates content, a refinement agent polishes the manuscript, and a plotting agent generates figures from code. The framework produces LaTeX output that matches target conference templates, including CVPR 2025.

Installation and usage

The framework is written in Python and requires Python 3.11. Install dependencies with:

pip install -r requirements.txt

Run the paper generation pipeline using the CLI:

python paper_writing_cli.py --raw_materials_dir /path_to_your_raw_materials/ --latex_template_dir /path_to_your_latex_template/ --output_dir /path_to_your_output_folder/ --use_plotting true

The framework also includes an interactive Streamlit demo in the frontend directory. To use external LLMs, create a .env file with API keys for OpenAI, Google Gemini, or Vertex AI, plus a Semantic Scholar API key for literature searches.

Current state and limitations

The repository has 4,436 stars and 549 forks on GitHub as of November 2026. The framework is licensed under Apache-2.0. The dataset used for paper generation is not included in the repository and will be released separately.

Go deeper


Get the latest AI updates in the Tech AI Magazine app
iPhone · Android