📦google-research / paper-orchestra
← 返回首页
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
⚖️ Apache-2.0#ai-research-assistant#multi-agent-systems🌐 yiwen-song.github.io📅 创建于 2026-05-01🔄 更新于 2026-11-15
🔗 GitHub Python
本站解读

PaperOrchestra 把写作拆成一支分工协调的 agent 团队,用于自动生成 AI 研究论文。输入可以是想法和实验日志这类没有固定格式的前期材料,输出目标则是可直接投稿的 LaTeX 稿件。流程覆盖大纲生成、文献综述、分节撰写、内容精修和绘图几个环节,其中文献部分会把已有工作汇总成综述,视觉部分除数据图表外还会产出概念示意图。论文写作中需要反复来回的几类工作,由此被放进同一条流水线里,适合手里有实验记录、需要快速整理成结构化稿件的科研人员,也适合研究多 agent 协作编排的开发者参考。语言为 Python,采用 Apache-2.0 许可。

上榜 2 天 · 首次上榜 2026-11-17 · 近 7 天 +1.5K star · 榜单最高 #4 · Apache-2.0

📄 仓库 README

在 GitHub 查看 ↗
来自 GitHub 仓库自述文件 · 版权归原作者所有

🎻 PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

Yiwen Song1, Yale Song1, Tomas Pfister1, and Jinsung Yoon1
1Google 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.

PaperOrchestra Overview

Key Features

  • 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.

Installation

  1. 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. bash conda create -n paper_orchestra python=3.11 conda activate paper_orchestra pip install -r requirements.txt

  2. Environment Variables: Create a .env file in the root of the project and add your API keys: ```env # 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 ```

Dataset

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.

Usage

You can run the paper generation pipeline using the provided bash script or directly via the Python CLI.

Using the Bash Script

./paper_writing_cli.sh

Using the Python CLI directly

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

Key Arguments

  • --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.

Interactive Demo

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.

Project Structure

  • 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.

Citation

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}
}

Disclaimer

This is not an officially supported Google product.

📈 近 7 天 Star 趋势

每日新增 Star(柱)与累计 Star(线)· 数据来自 GitHub

🏆 排名变化趋势

在各榜单中的排名历史(数字越小越靠前)

📋 历史上榜记录

每次快照的详细数据
日期 榜单 排名 周期新增 总 STAR