AutoGluon Assistant (aka MLZero)

Official implementation of MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

AutoGluon Assistant (aka MLZero) is a multi-agent system that automates end-to-end multimodal machine learning or deep learning workflows by transforming raw multimodal data into high-quality ML solutions with zero human intervention. Leveraging specialized perception agents, dual-memory modules, and iterative code generation, it handles diverse data formats while maintaining high success rates across complex ML tasks.

💾 Installation

AutoGluon Assistant is supported on Python 3.8 - 3.11 and is available on Linux (will fix dependency issues for MacOS and Windows by our next official release).

You can install from source (new version will be released to PyPI soon):

pip install uv
uv pip install git+https://github.com/autogluon/autogluon-assistant.git

Quick Start

For detailed usage instructions, OpenAI/Azure setup, and advanced configuration options, see our Getting Started Tutorial.

API Setup

MLZero uses AWS Bedrock by default. Configure your AWS credentials:

export AWS_DEFAULT_REGION="<your-region>"
export AWS_ACCESS_KEY_ID="<your-access-key>"
export AWS_SECRET_ACCESS_KEY="<your-secret-key>"

We also support OpenAI. More LLM providers' support (e.g. Anthropic, Azure, etc.) will be added soon.

Basic Usage

mlzero -i <input_data_folder> [-u <optional_user_instructions>]

Citation

If you use Autogluon Assistant (MLZero) in your research, please cite our paper:

@misc{fang2025mlzeromultiagentendtoendmachine,
      title={MLZero: A Multi-Agent System for End-to-end Machine Learning Automation}, 
      author={Haoyang Fang and Boran Han and Nick Erickson and Xiyuan Zhang and Su Zhou and Anirudh Dagar and Jiani Zhang and Ali Caner Turkmen and Cuixiong Hu and Huzefa Rangwala and Ying Nian Wu and Bernie Wang and George Karypis},
      year={2025},
      eprint={2505.13941},
      archivePrefix={arXiv},
      primaryClass={cs.MA},
      url={https://arxiv.org/abs/2505.13941}, 
}