Auto outline & review from raw ideas
This repo lets you auto‐create a detailed outline and a curated literature review directly from your raw ideas and experiment logs, saving you hours of manual searching.
google-research/paper-orchestra
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
THE USEFUL PART
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
THE STACKRADAR WALKTHROUGH
A short introduction from our reel. See the project README for the current details.
This repo lets you auto‐create a detailed outline and a curated literature review directly from your raw ideas and experiment logs, saving you hours of manual searching.
It then formats everything into a submission‐ready LaTeX manuscript that follows the exact conference template you provide, so the final document meets all formatting rules automatically.
Finally, the plotting agent builds charts and conceptual diagrams from your code, inserting them straight into the manuscript so you get complete figures without leaving the pipeline.
GITHUB SNAPSHOT
Recorded counts, not a growth rate or a quality score.
OBSERVED STAR HISTORY
2 real daily observations. 1.3k → 2.8k stars.

FROM THE PROJECT
Source excerpts from the project's README. Not an independent review, verification or security audit.
Yiwen Song 1 , Yale Song 1 , Tomas Pfister 1 , and Jinsung Yoon 1 1 Google Cloud AI Research
PaperOrchestra is a multi-agent framework for automated AI research paper writing. It flexibly transforms unconstrained pre-writing materials (ideas and experimental logs) into submission-ready LaTeX manuscripts, including comprehensive literature synthesis and generated visuals, such as plots and conceptual diagrams.
Acting like an orchestrated team of specialized agents, it handles outline generation, literature review, section writing, content refinement, and plotting to close the gap between raw research materials and submission ready papers.
Multi-Agent Pipeline: Orchestrates specialized agents (Outline, Literature Review, Section Writing, Content Refinement, Plotting) for end-to-end paper generation.
Comprehensive Literature Synthesis: Automatically searches, prioritizes, and integrates relevant literature into the manuscript.
Visuals Generation: Generates plots and supports the inclusion of conceptual diagrams.
LaTeX Automation: Produces submission-ready LaTeX manuscripts adhering to target conference templates.
Environment Setup: The project relies on a Conda environment named paper_orchestra. You can set up a similar environment with Python 3.11 and install the required dependencies.
conda create -n paper_orchestra python=3.11
conda activate paper_orchestra
pip install -r requirements.txt
Environment Variables: Create a .env file in the root of the project and add your API keys:
# Add keys if you have them, otherwise leave them empty
# You need to specify related keys if you want to use the model
# For example, if you want to use Gemini models, you need to specify either VERTEX_AI_PROJECT and VERTEX_AI_LOCATION, or GEMINI_API_KEY
# If you want to use OpenAI models, you need to specify OPENAI_API_KEY
SEMANTIC_SCHOLAR_API_KEY=your_semantic_scholar_api_key
OPENAI_API_KEY=your_openai_api_key
VERTEX_AI_PROJECT=your_vertex_ai_project
VERTEX_AI_LOCATION=your_vertex_ai_location
GEMINI_API_KEY=your_gemini_api_key
# if you want to run demo and send emails to yourself at the end, set these 2 fields as well
SMTP_EMAIL=your_email
SMTP_PASSWORD=your_password
The dataset used for paper generation is not included in this code repository. It will be released separately at a later date. Once available, you should download the dataset and place it under the datasets/ directory.
You can run the paper generation pipeline using the provided bash script or directly via the Python CLI.
./paper_writing_cli.sh
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
--raw_materials_dir: (Required) Directory containing the raw materials (e.g., idea and experimental log).
--latex_template_dir: (Required) Directory containing the LaTeX template (e.g., templates/cvpr2025).
--output_dir: Directory to output the generated paper. If not specified, an automatic folder with a timestamp is created.
--use_plotting: Enable the plotting agent workflow to generate figures from code (Default: False).
--writer_model_name: LLM for writer and literature agents.
--reflection_model_name: LLM for reflection agents.
We provide an interactive Streamlit demo for the paper generation pipeline. For instructions on how to run and use it, please refer to the README.md in the frontend directory.
autoraters/: Contains scripts for automated evaluation.
methods/: Core logic for agents and pipeline execution.
templates/: LaTeX templates for target conferences, you can add your own template by creating a new subfolder under this directory.
utils/: Utility functions for API calls, PDF handling, etc.
If you find this repo or our paper helpful, please cite it as follows:
@article{song2026paperorchestra,
title={PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing},
author={Song, Yiwen and Song, Yale and Pfister, Tomas and Yoon, Jinsung},
journal={arXiv preprint arXiv:2604.05018},
year={2026}
}
This is not an officially supported Google product.
Read the original READMEKEEP EXPLORING
Repository preview
strelov1/freehire
Open-source search engine aggregating 3.3M+ tech jobs directly from 294k+ company career pages. Zero recruiters, no reposts.
git clone https://github.com/strelov1/freehire.gitzenhostai/9drive
Virtual storage gateway pooling multiple free Google Drive accounts into a combined 60GB+ high-speed personal bucket.
git clone https://github.com/zenhostai/9drive.git
Repository screenshot
rive-app/rive-unreal
Unreal Engine runtime for Rive, the agent-native 2D and 3D engine for games, apps, and interactive UI.
git clone https://github.com/rive-app/rive-unreal.gitShort demos. New discoveries. Less noise in your feed.