Will the next scientific revolution be driven by AI agents?

Synopsis

Science advances by formulating and testing hypotheses, collecting and analyzing data, and drawing conclusions—yet much of a scientist’s time is spent in tasks such as coding analyses, writing and revising text, reviewing the literature, and learning new concepts. Can recent advances in AI help reclaim some of that time? In this talk, I will show how large language models and AI agents may help scientists with these tasks. I will first describe what AI agents are and discuss their applications in science. Next, I will present Denario, a complex, publicly available, multi-AI-agent system designed to function as a research assistant. Developed and evaluated by a diverse team of scientists, mathematicians, and philosophers, Denario is an interdisciplinary tool capable of generating ideas, searching the literature, developing research plans, writing and executing code, crafting plots, and drafting and reviewing scientific papers. I will also present and discuss some of the papers that Denario generated a couple of years ago in disciplines such as astrophysics, biology, biophysics, biomedical informatics, chemistry, machine learning, materials science, mathematical physics, medicine, neuroscience, planetary physics, and quantum physics. I will then present Denario2, designed to generate scientific knowledge at scale by deploying swarms of AI agents that run autonomously for weeks to months. Finally, I will discuss ethical and philosophical aspects of this kind of research and open a discussion about the role of humans in science.