The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Учёный ИИ: к полностью автоматизированному открытому научному поиску
Jeff Clune, Chris J. J. Lu, Cong Lu, R. T. Lange, Jakob Foerster, David Ha, Lange, Robert Tjarko
2024-08-12

AI Scientistautomated paper reviewautomated scientific discoverylarge language modelsopen-ended research
One of the grand challenges of artificial general intelligence is developing agents capable of conducting scientific research and discovering new knowledge. While frontier models have already been used as aides to human scientists, e.g. for brainstorming ideas, writing code, or prediction tasks, they still conduct only a small part of the scientific process. This paper presents the first comprehensive framework for fully automatic scientific discovery, enabling frontier large language models to perform research independently and communicate their findings. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, describes its findings by writing a full scientific paper, and then runs a simulated review process for evaluation. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community. We demonstrate its versatility by applying it to three distinct subfields of machine learning: diffusion modeling, transformer-based language modeling, and learning dynamics. Each idea is implemented and developed into a full paper at a cost of less than $15 per paper. To evaluate the generated papers, we design and validate an automated reviewer, which we show achieves near-human performance in evaluating paper scores. The AI Scientist can produce papers that exceed the acceptance threshold at a top machine learning conference as judged by our automated reviewer. This approach signifies the beginning of a new era in scientific discovery in machine learning: bringing the transformative benefits of AI agents to the entire research process of AI itself, and taking us closer to a world where endless affordable creativity and innovation can be unleashed on the world's most challenging problems. Our code is open-sourced at https://github.com/SakanaAI/AI-Scientist
1
Some AI Scientist-generated papers exceeded the acceptance threshold of a top machine learning conference according to the automated reviewer.
2
The AI Scientist is presented as a comprehensive framework enabling frontier language models to conduct scientific research largely autonomously.
3
The authors designed and validated an automated reviewer that achieves near-human performance in evaluating scientific paper scores.
4
The framework was demonstrated across diffusion modeling, transformer-based language modeling, and learning dynamics, with each paper costing less than $15 to produce.
5
The system generates research ideas, writes and executes code, visualizes experiments, authors full scientific papers, and performs simulated peer review.

The AI Scientist system (an autonomous framework using frontier large language models to generate research ideas, run experiments, write papers, and perform review)

The framework’s capability to autonomously perform the end-to-end research process and generate, evaluate, and communicate novel machine-learning research

Publication Details
Publication Date
2024-08-12
Journal
Publisher
ISSN
Cited by
1914
Access Type
Author Information
Authors
Jeff Clune
Chris J. J. Lu
Cong Lu
R. T. Lange
Jakob Foerster
David Ha
Lange, Robert Tjarko
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%