The holy grail for scientists is to focus on their research to enhance and produce scientific discoveries while offloading time-consuming tasks. So-called artificial intelligence (AI) co-scientists are helping to make this possible. These collaborative AI systems are designed to assist human researchers by accelerating scientific discovery, enhancing collaboration, analyzing data, and going beyond human intuition. An AI co-scientist performs various scientific tasks, especially in areas like hypothesis generation, experimental design, verification, and literature review. It uses the results to learn to improve its ability to generate and refine hypotheses.

Large Language Models (LLMs) are playing an increasingly important role in physics research by assisting with symbolic manipulation, numerical computation, and scientific reasoning. However, ensuring the reliability, transparency, and interpretability of their outputs remains a major challenge. In this work, we introduce a novel multi-agent LLM physicist framework that fosters collaboration between AI and human scientists through three key modules: a reasoning module, an interpretation module, and an AI-scientist interaction module. Recognizing that effective physics reasoning demands logical rigor, quantitative accuracy, and alignment with established theoretical models, we propose an interpretation module that employs a team of specialized LLM agents-including summarizers, model builders, visualization tools, and testers-to systematically structure LLM outputs into transparent, physically grounded science models. A case study demonstrates that our approach significantly improves interpretability, enables systematic validation, and enhances human-AI collaboration in physics problem-solving and discovery. Our work bridges free-form LLM reasoning with interpretable, executable models for scientific analysis, enabling more transparent and verifiable AI-augmented research.

To hear Silicon Valley tell it, the end of disease is well on its way. Demis Hassabis, a Nobel laureate for his AI research and the CEO of Google DeepMind, said on Sunday that he hopes that AI will be able to solve important scientific problems and help "cure all disease" within five to 10 years. Earlier this month, OpenAI released new models and touted their ability to "generate and critically evaluate novel hypotheses" in biology, among other disciplines. These are all executives marketing their products, obviously, but is there even a kernel of possibility in these predictions? If generative AI could contribute in the slightest to such discoveries--as has been promised since the start of the AI boom--where would the technology and scientists using it even begin?

AI-powered autonomous experimentation (AI/AE) can accelerate materials discovery but its effectiveness for electronic materials is hindered by data scarcity from lengthy and complex design-fabricate-test-analyze cycles. Unlike experienced human scientists, even advanced AI algorithms in AI/AE lack the adaptability to make informative real-time decisions with limited datasets. Here, we address this challenge by developing and implementing an AI decision interface on our AI/AE system. The central element of the interface is an AI advisor that performs real-time progress monitoring, data analysis, and interactive human-AI collaboration for actively adapting to experiments in different stages and types. We applied this platform to an emerging type of electronic materials-mixed ion-electron conducting polymers (MIECPs) -- to engineer and study the relationships between multiscale morphology and properties. Using organic electrochemical transistors (OECT) as the testing-bed device for evaluating the mixed-conducting figure-of-merit -- the product of charge-carrier mobility and the volumetric capacitance (μC*), our adaptive AI/AE platform achieved a 150% increase in μC* compared to the commonly used spin-coating method, reaching 1,275 F cm-1 V-1 s-1 in just 64 autonomous experimental trials. A study of 10 statistically selected samples identifies two key structural factors for achieving higher volumetric capacitance: larger crystalline lamellar spacing and higher specific surface area, while also uncovering a new polymer polymorph in this material.

How do AI scientists stack up to human ones? Human scientists and engineers can still outperform agents based on an advanced artificial intelligence model in a game that mimics the process of scientific discovery. But this simulation could ultimately help researchers develop AI agents that can outcompete humans. AI models are developing a reputation for science discovery – they can, for instance, predict how protein molecules will interact – but they still perform best when trained to solve a particular type of problem.

Artificial intelligence (AI) models trained on published scientific findings have been used to invent valuable materials and targeted therapies, but they typically ignore the human scientists who continually alter the landscape of discovery. Here we show that incorporating the distribution of human expertise by training unsupervised models on simulated inferences cognitively accessible to experts dramatically improves (up to 400%) AI prediction of future discoveries beyond those focused on research content alone, especially when relevant literature is sparse. These models succeed by predicting human predictions and the scientists who will make them. By tuning human-aware AI to avoid the crowd, we can generate scientifically promising "alien" hypotheses unlikely to be imagined or pursued without intervention until the distant future, which hold promise to punctuate scientific advance beyond questions currently pursued. Accelerating human discovery or probing its blind spots, human-aware AI enables us to move toward and beyond the contemporary scientific frontier.

Transforming materials discovery plays a pivotal role in addressing global challenges. The applications of new materials could range from clean energy storage, to sustainable polymers and packaging for consumer products towards a more circular economy, to drugs and therapeutics. Stemming from the COVID-19 pandemic, where scientists had to halt experiments due to stringent social distancing measures or accelerate their efforts towards quickly producing a vaccine, there has recently been an increased interest in using robotics and automation in laboratory environments. The challenge here is that laboratories have been designed by and for humans and thus the available glassware, tools and equipment pose difficult problems for traditional automation methods that are inherently open loop and not adaptable. Learning-based methods that rely on autonomous trial and error are increasingly being used to achieve robotic tasks that could not be previously addressed with automation.

Science has been the most important tool of humanity even before the dawn of history. Humans have used science, without even knowing that they are scientists, to understand and improve every aspect of their lives. For many thousands of years, the way to handle, make sense of and address the experiences of life was through the use of science (and myth). "The purpose of science and art is one: to render experiences intelligible, i.e., to assist man to adjust himself and the environment in order that he may live" (White, 1938). Although the term'science' had different meaning than the one we use today, throughout history the knowledge created by science enabled humanity to create technologies.