2026/07/30 by Qi Wang, Long-Gang Pang, Shi Pu +1
Physics and Astronomy · #nucl-th #hep-ph
15 pages, 6 figures
arxiv created 2026/07/30 · arxiv updated 2026/07/31
We enable large language model (LLM) agents to autonomously perform end-to-end hydrodynamic simulations of the quark-gluon plasma evolution and calculation of final hadron spectra in relativistic heavy-ion collisions. We design a meta skill that allows an agent to explore a project's source code, craft a specialized skill, and iteratively refine it. Applying this meta skill to the (3+1)D viscous hydrodynamic code CLVisc, the agent builds a CLVisc skill encoding its operational knowledge and then independently executes full scientific workflows: designing parameter scans, running simulations, comparing ensemble results, and producing publication-ready figures. Crucially, the agent draws on literature-informed heavy-ion physics to select physically meaningful observables and interpret outcomes without explicit instruction. We demonstrate the pipeline in two scenarios: temperature-dependent shear viscosity over entropy density η/s, and nuclear-structure effects in O+O collisions at √sNN = 5.36~TeV using four ab initio descriptions of 16O. In both, the agent plans, executes, and analyzes autonomously, devising new initial-state observables to explain final observations and extract qualitative knowledge. The meta skill is agnostic to code versions and Monte Carlo generators, promising future multi-agent systems in high-energy nuclear physics.