Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics

ArXi:2604.12198v1 Announce Type: cross Recent autonomous LLM agents have nstrated end-to-end automation of machine-learning research. Real-world physical science is intrinsically harder, requiring deep reasoning bounded by physical truth and, because real systems are too complex to study in isolation, almost always built on existing literature. We focus on the smallest meaningful unit of such research, a mini research loop in which an agent reads a paper, reproduces it, critiques it, and extends it. We test this loop in two complementary regimes: scale and depth.