A system of artificial intelligence developed by Sakana AI in collaboration with Canadian and British researchers has demonstrated its ability to conduct scientific research from start to finish, from generating ideas to writing articles. Published in Nature, this system successfully submitted an article to an academic conference, marking a significant advancement in research automation.
A system capable of autonomously conducting scientific research, from idea conception to drafting complete articles, represents a milestone in the evolution of the relationship between artificial intelligence and the scientific method. Developed by Sakana AI in collaboration with researchers from the University of British Columbia, the Vector Institute, and the University of Oxford, this system named AI Scientist functions as a complete virtual researcher.
The mechanism is based on foundational models that orchestrate each phase of the scientific work. It generates research ideas, explores academic literature to verify the originality of proposals, writes and corrects code to conduct experiments, analyzes the obtained results, produces data visualizations, writes manuscripts in LaTeX, and even evaluates the quality of its own production. “This article marks the dawn of a new chapter in human history, where scientific progress is radically accelerated by AI scientists capable of autonomous action,” highlights Jeff Clune, a computer science professor at UBC and lead author of the publication.
The team has also developed an automated evaluator capable of predicting acceptance decisions at a conference with performance comparable to human reviewers. This component has led to the establishment of what researchers describe as a scalability law: the quality of the produced articles improves proportionally to the capabilities of the underlying foundational models and the allocated computing power.
To evaluate the system’s performance according to academic standards, researchers submitted three articles entirely generated by artificial intelligence to a workshop at the International Conference on Learning Representations in 2025. One of these articles, focusing on the regularization of neural networks, received an average score of 6.33 out of 10 from human reviewers. This performance placed it above around 55% of all submissions and exceeded the workshop’s acceptance threshold.
In accordance with an agreement with the conference organizers, Sakana AI withdrew the article before publication, citing the absence of established standards regarding AI-generated manuscripts.
Despite these limitations, the potential implications of this technology have drawn the attention of the scientific community. “AI Scientist paves the way for recursive improvement in which the AI system not only discovers new scientific knowledge but also uses these discoveries to become better at making further discoveries,” explains Shengran Hu, a UBC doctoral student and study co-author.
An editorial in Nature published parallel to the scientific article points out that the system “raises unanswered questions about how research should be conducted and governed as AI-driven automation accelerates.”
The emergence of systems capable of automating the entire scientific process poses fundamental challenges for the future of research. While the technology accelerates certain phases of scientific work, it also raises questions about the role of human intuition, creativity, and responsibility in knowledge production.
Paper: Lu et al. (2026). Towards end-to-end automation of AI research. Nature. DOI: 10.1038/s41586-026-10265-5
