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 full article writing, 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.
Automated Scientific Process
The mechanism relies on foundational models that orchestrate each phase of scientific work. It generates research ideas, explores academic literature to verify the originality of proposals, writes and corrects code to conduct experiments, analyzes the results obtained, produces data visualizations, writes manuscripts in LaTeX, and evaluates the quality of its own production. “This article marks the dawn of a new chapter in human history, where scientific progress is revolutionized by AI scientists capable of acting autonomously,” emphasizes Jeff Clune, a computer science professor at UBC and lead author of the publication.
The team also developed an automated evaluator capable of predicting acceptance decisions at conferences with performance comparable to human evaluators. This component helped establish what researchers describe as a scaling law: the quality of produced articles improves proportionally to the capabilities of underlying foundational models and allocated computing power.
Real-world Testing
To evaluate the system’s performance against 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 neural network regularization, received an average score of 6.33 out of 10 from human evaluators. This performance placed it above approximately 55% of all submissions and exceeded the workshop’s acceptance threshold.
According to an agreement with the conference organizers, Sakana AI withdrew the article before publication, citing the absence of established standards for AI-generated manuscripts.
Current Capabilities and Limitations
Researchers acknowledge several shortcomings in the current system:
1. It sometimes produces underdeveloped ideas. 2. It generates inaccurate citations. 3. It is currently limited to computer science research.
Sakana AI indicated that none of its three submissions to ICLR met internal standards for publication in the conference’s main session. The accepted article only passed through a workshop session with an acceptance rate of 60 to 70 percent.
Despite these limitations, the potential implications of this technology have attracted the scientific community’s attention. “The AI Scientist paves the way for recursive improvement in which the AI system not only discovers new scientific knowledge but uses these discoveries to become better at realizing further discoveries,” explains Shengran Hu, a UBC doctoral student and study co-author.
An editorial in Nature published parallel to the scientific article emphasizes 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 allows for accelerating 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
