Preprint · 2024 · Open access
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
arXiv (Cornell University) · Published 12 August 2024 · DOI 10.48550/arxiv.2408.06292
In brief
“The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery” is a 2024 preprint by Chris J. J. Lu and 5 co-authors, published in arXiv (Cornell University). OpenAlex counts 1,912 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 1,912
- Most cited in
- 2026 (1,232)
- References
- 93
- Authors
- 6
Abstract
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
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Lu, C. J. J., Lu, C., Tjarko, L. R., Foerster, J., Clune, J., & Ha, D. (2024). The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2408.06292
MLA 9
Lu, Chris J. J., et al. “The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2408.06292.
Chicago
Lu, Chris J. J., Cong Lu, Lange, Robert Tjarko, Jakob Foerster, Jeff Clune, and David Ha. 2024. “The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2408.06292.
Harvard
Lu, C. J. J. et al. (2024) ‘The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery’, arXiv (Cornell University). doi:10.48550/arxiv.2408.06292.
IEEE
C. J. J. Lu, C. Lu, L. R. Tjarko, J. Foerster, J. Clune, and D. Ha, “The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2408.06292.
BibTeX
@misc{lu2024scientist,
title = {{The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery}},
author = {Lu, Chris J. J. and Lu, Cong and Tjarko, Lange, Robert and Foerster, Jakob and Clune, Jeff and Ha, David},
howpublished = {arXiv (Cornell University)},
year = {2024},
doi = {10.48550/arxiv.2408.06292},
url = {https://doi.org/10.48550/arxiv.2408.06292}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2017 | 1 | |
| 2019 | 1 | |
| 2023 | 4 | |
| 2024 | 83 | |
| 2025 | 591 | |
| 2026 | 1,232 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- AI scientists
- automated scientific discovery
- large language models
- automated peer review
- research idea generation
- code generation
- diffusion models
- learning dynamics
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Lu, C. J. J., Lu, C., Tjarko, L. R., Foerster, J., Clune, J., & Ha, D. (2024). The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2408.06292
How many times has this paper been cited?
1,912 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Chris J. J. Lu, Cong Lu, Lange, Robert Tjarko, Jakob Foerster, Jeff Clune, David Ha.
What is the DOI of this paper?
10.48550/arxiv.2408.06292, permanently at https://doi.org/10.48550/arxiv.2408.06292. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.