Automated Many-Body Simulations of Strongly Correlated Systems Using a Correlation-Aware Agentic Framework
Abstract
We present CAFES, a correlation-aware agentic framework for electronic-structure simulations of strongly correlated systems. CAFES addresses two challenges: the fragmented software landscape for many-body calculations and the difficulty of selecting appropriate methods across diverse correlation regimes. It combines correlation diagnostics, adaptive method selection, and large language model (LLM) assistance for molecular, crystalline, and model-Hamiltonian systems. A study-task architecture separates study-level planning from task-level execution, while a curated scientific knowledge layer provides reusable guidance for method selection, workflow design, and result interpretation. We demonstrate CAFES through three research-level studies: calculating the low-lying electronic states of lutein using DMRG-CASSCF, probing phase competition in the extended honeycomb Hubbard model using DMET, and generating a quantum-chemical dataset with CCSD labels. These calculations demonstrate the potential of agentic workflows for strongly correlated electronic-structure problems, a regime that has received limited attention in existing agentic computational frameworks.
Related
- POLEN: An OpenMM Framework for ML/MM Simulations with Mutually Polarizable AMOEBA Embedding
- A scalable framework for goal-driven task-based simulations
- Nonempirical Time-Dependent Density Functional Theory Framework for Nonlocal Exchange--Correlation Potentials
- Electron Density of Delocalized Bonds from Correlated One-Particle Density Matrices
- A linear-scaling explicitly correlated local natural orbital CCSD(T) approach
BibTeX
@misc{li2026automated,
title = {{Automated Many-Body Simulations of Strongly Correlated Systems Using a Correlation-Aware Agentic Framework}},
author = {Tenghui Li and Chong Sun},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.00943},
eprint = {2610.00943},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.00943},
}
RIS
TY - UNPB
TI - Automated Many-Body Simulations of Strongly Correlated Systems Using a Correlation-Aware Agentic Framework
AU - Tenghui Li
AU - Chong Sun
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.00943
UR - https://arxiv.org/abs/2610.00943
AB - We present CAFES, a correlation-aware agentic framework for electronic-structure simulations of strongly correlated systems. CAFES addresses two challenges: the fragmented software landscape for many-body calculations and the difficulty of selecting appropriate methods across diverse correlation regimes. It combines correlation diagnostics, adaptive method selection, and large language model (LLM) assistance for molecular, crystalline, and model-Hamiltonian systems. A study-task architecture separates study-level planning from task-level execution, while a curated scientific knowledge layer provides reusable guidance for method selection, workflow design, and result interpretation. We demonstrate CAFES through three research-level studies: calculating the low-lying electronic states of lutein using DMRG-CASSCF, probing phase competition in the extended honeycomb Hubbard model using DMET, and generating a quantum-chemical dataset with CCSD labels. These calculations demonstrate the potential of agentic workflows for strongly correlated electronic-structure problems, a regime that has received limited attention in existing agentic computational frameworks.
ER -