Artificial intelligence (AI) is used in numerous fields of science, yet the initial research questions and targets are still almost always provided by human researchers. AI-generated creative ideas in science are rare and often vague, so that it remains a human task to execute them. Automating idea generation and implementation in one coherent system would significantly shift the role of humans in the scientific process. Here we present AI-Mandel, an LLM agent that can generate and implement ideas in quantum physics. AI-Mandel formulates ideas from the literature and uses a domain-specific AI tool to turn them into concrete experiment designs that can readily be implemented in laboratories. The generated ideas by AI-Mandel are often scientifically interesting - for two of them we have already written independent scientific follow-up papers. The ideas include new variations of quantum teleportation, primitives of quantum networks in indefinite causal orders, and new concepts of geometric phases based on closed loops of quantum information transfer. AI-Mandel is a prototypical demonstration of an AI physicist that can generate and implement concrete, actionable ideas. Building such a system is not only useful to accelerate science, but it also reveals concrete open challenges on the path to human-level artificial scientists.

Generative Artificial Intelligence (AI) models can propose solutions to scientific problems beyond human capability. To truly make conceptual contributions, researchers need to be capable of understanding the AI-generated structures and extracting the underlying concepts and ideas. When algorithms provide little explanatory reasoning alongside the output, scientists have to reverse-engineer the fundamental insights behind proposals based solely on examples. This task can be challenging as the output is often highly complex and thus not immediately accessible to humans. In this work we show how transferring part of the analysis process into an immersive Virtual Reality (VR) environment can assist researchers in developing an understanding of AI-generated solutions. We demonstrate the usefulness of VR in finding interpretable configurations of abstract graphs, representing Quantum Optics experiments. Thereby, we can manually discover new generalizations of AI-discoveries as well as new understanding in experimental quantum optics. Furthermore, it allows us to customize the search space in an informed way - as a human-in-the-loop - to achieve significantly faster subsequent discovery iterations. As concrete examples, with this technology, we discover a new resource-efficient 3-dimensional entanglement swapping scheme, as well as a 3-dimensional 4-particle Greenberger-Horne-Zeilinger-state analyzer. Our results show the potential of VR for increasing a human researcher's ability to derive knowledge from graph-based generative AI that, which is a common abstract data representation used in diverse fields of science.

Quantum physicist Mario Krenn remembers sitting in a café in Vienna in early 2016, poring over computer printouts, trying to make sense of what MELVIN had found. MELVIN was a machine-learning algorithm Krenn had built, a kind of artificial intelligence. Its job was to mix and match the building blocks of standard quantum experiments and find solutions to new problems. And it did find many interesting ones. But there was one that made no sense.

Quantum physicist Mario Krenn remembers sitting in a café in Vienna in early 2016, poring over computer printouts, trying to make sense of what MELVIN had found. MELVIN was a machine-learning algorithm Krenn had built, a kind of artificial intelligence. Its job was to mix and match the building blocks of standard quantum experiments and find solutions to new problems. And it did find many interesting ones. But there was one that made no sense.

Quantum physicist Mario Krenn remembers sitting in a café in Vienna in early 2016, poring over computer printouts, trying to make sense of what MELVIN had found. MELVIN was a machine-learning algorithm Krenn had built, a kind of artificial intelligence. Its job was to mix and match the building blocks of standard quantum experiments and find solutions to new problems. And it did find many interesting ones. But there was one that made no sense. "The first thing I thought was, 'My program has a bug, because the solution cannot exist,'" Krenn says.

In 2016, Mario Krenn, Anton Zeilinger and colleagues at the IQOQI-Vienna of the Austrian Academy of Sciences (ÖAW) and at the University of Vienna have developed the algorithm Melvin, which can automatically design new quantum experiments for which the human scientists had no answer until then [1]. Since then, several of these experiments have been successfully implemented in the laboratories of Zeilinger group [2-4]. Also, the unintuitive solutions of the algorithm have led to new ideas and connections in quantum physics [5,6]. In the more recent study "Active learning machine learns to create new quantum experiments" [7] the Viennese physicists have joined forces with the group of Hans Briegel from the University of Innsbruck, engaged in research at the boundary between quantum physics and artificial intelligence, to expand Melvin's ability with Artificial Intelligence. This research has now been chosen to represent scientific excellence and originality in the class of Physical and Mathematical Sciences of the Cozzarelli prize.

Quantum physics can fly in the face of human intuition--even that of a physicist such as Mario Krenn at the University of Vienna. This counterintuitive quality makes it difficult for researchers to design experiments to explore the field. Now, to avoid intuitive pitfalls, Krenn and his colleagues have devised a computer program to automatically design new quantum experiments that they would not have thought of themselves. The way that all known particles behave can be explained with quantum physics. A major feature of this branch of physics is that the world becomes a vague, bizarre place at its very smallest levels. For example, atoms and other basic building blocks of the universe can exist in states of flux known as superpositions, meaning they can seemingly be located in two or more places at the same time, or spin in opposite directions simultaneously; and with the phenomenon of quantum entanglement, two or more objects can get connected such that what happens to one instantaneously affects whatever is linked to it, no matter how far apart they are in the universe.