AIRAS is an open-source software framework for automated research, being developed to support the entire research workflow. It aims to integrate all of the necessary functions for automating research—from literature search and method generation to experimentation and paper writing—and is designed with the aim of enabling as many individuals and organizations as possible to contribute to open innovation in research automation.

Currently, it focuses on the automation of machine learning research.

Unlike other automated research agents such as AI Scientist, AIRAS has the following key features:

Features

• Implemented by individual research processes
• Enables users to implement flexible and customized research workflows
• Allows users to add their own original research processes

Preparing. Please wait a moment.

• Complete automation of machine learning research with code-based experimentation
• Autonomous research in Research in simulated robotic environments
• Autonomous research in Real-world robotics research.
• Laboratory Automation and autonomous research in various fields

We are exploring best practices for human-AI collaboration in automated AI research. Together, we're investigating how new research workflows—powered by both human insight and AI agents—can accelerate discovery, improve reproducibility, and give organizations a competitive edge in the age of autonomous research.

If you are interested in this topic, please feel free to contact us at [email protected].

This OSS is developed as part of the AutoRes project.

If you use AIRAS in your research, please cite as follows:

@software{airas2025,
  author = {Toma Tanaka, Takumi Matsuzawa, Yuki Yoshino, Ilya Horiguchi, Shiro Takagi, Ryutaro Yamauchi, Wataru Kumagai},
  title = {AIRAS},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/airas-org/airas}
}