Preprint · 2024 · Open access

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

Chris J. J. Lu, Cong Lu, Lange, Robert Tjarko, Jakob Foerster, Jeff Clune, David Ha

arXiv (Cornell University) · Published 12 August 2024 · DOI 10.48550/arxiv.2408.06292

Open PDFView at the publisherCite this paper

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

YearCitationsShare of the best year
201711
201911
202344
20248383
2025591591
20261,2321232

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

All highly cited Computer Science papers

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.