Researchers have developed a new artificial intelligence (AI) model called MagNet that can predict the behavior of complex quantum systems. The model uses a self-attention neural network to analyze the interactions between particles in a magnetic field and has been shown to accurately describe both liquid states and crystalline structures. This work demonstrates the potential of first-principles AI for solving complex many-body problems without requiring external training data or prior knowledge of physics. --- Why it matters: This research matters because it provides a new tool for understanding and predicting the behavior of quantum systems, which are crucial in fields such as materials science and condensed matter physics. The ability to accurately model these systems could lead to breakthroughs in fields like superconductivity and topological insulators. Source: https://arxiv.org/abs/2602.03927