UrQMD-Agent: An LLM-Assisted Framework for Microscopic Tracing of Proton Azimuthal Correlations
Abstract
We present an LLM-assisted framework for microscopic transport studies that connects a general-purpose large language model (LLM) to the UrQMD transport model through a model-specific Skill and a deterministic scientific tool layer. The LLM supports literature-guided scientific planning and interpretation, while numerical calculations, event-history reconstruction, and statistical analyses are performed by deterministic tools. As a demonstration, the framework is applied to proton azimuthal-partition fluctuations in Au+Au collisions at √(sNN)=3.0--39~GeV. In the 0--5\% centrality class, the fluctuations are statistically resolved below zero from 3 to 27~GeV and consistent with zero at 39~GeV. An exact pair-kernel decomposition shows that the negative signal is carried mainly by proton pairs containing at least one decay-fed proton. A random-label null test further distinguishes the observed pair contributions from expectations based on pair abundance alone. Reaction-history tracing shows that, for pairs of two decay-fed protons, the negative pair-kernel contribution is already present in the parent momenta evaluated at their respective formation vertices. The modular architecture is designed to accommodate different general-purpose LLMs and can be extended to other microscopic transport models through dedicated Skills and tool interfaces. This provides a pathway toward systematic microscopic analyses and comparisons across transport models within a common LLM-assisted framework.
Related
- Microscopic Parametric Correlations and Spectral Rigidity in the Non-Hermitian Threefold Way
- Quantum Fluctuations in Bose--Einstein Condensates:Microscopic Correlations and Moment Bounds
- Spin-outcome correlations and memory-assisted entropic uncertainty in Bhabha scattering with an entangled spectator
- Systematic calculations of β-delayed fission probabilities using a microscopic framework
- A No-Go Framework for Coarse-Grained Effect Prediction in Boron Neutron Capture Therapy: Structural Identifiability Limits and Microscopic Coverage
BibTeX
@misc{li2026urqmdagent,
title = {{UrQMD-Agent: An LLM-Assisted Framework for Microscopic Tracing of Proton Azimuthal Correlations}},
author = {Fu-Peng Li and Yige Huang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.30198},
eprint = {2610.30198},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.30198},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - UrQMD-Agent: An LLM-Assisted Framework for Microscopic Tracing of Proton Azimuthal Correlations
AU - Fu-Peng Li
AU - Yige Huang
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2610.30198
UR - https://arxiv.org/abs/2610.30198
AB - We present an LLM-assisted framework for microscopic transport studies that connects a general-purpose large language model (LLM) to the UrQMD transport model through a model-specific Skill and a deterministic scientific tool layer. The LLM supports literature-guided scientific planning and interpretation, while numerical calculations, event-history reconstruction, and statistical analyses are performed by deterministic tools. As a demonstration, the framework is applied to proton azimuthal-partition fluctuations in Au+Au collisions at √(s_NN)=3.0--39~GeV. In the 0--5\% centrality class, the fluctuations are statistically resolved below zero from 3 to 27~GeV and consistent with zero at 39~GeV. An exact pair-kernel decomposition shows that the negative signal is carried mainly by proton pairs containing at least one decay-fed proton. A random-label null test further distinguishes the observed pair contributions from expectations based on pair abundance alone. Reaction-history tracing shows that, for pairs of two decay-fed protons, the negative pair-kernel contribution is already present in the parent momenta evaluated at their respective formation vertices. The modular architecture is designed to accommodate different general-purpose LLMs and can be extended to other microscopic transport models through dedicated Skills and tool interfaces. This provides a pathway toward systematic microscopic analyses and comparisons across transport models within a common LLM-assisted framework.
ER -