Agentic Systems for Calibrating Cosmological Simulations
Abstract
Calibrating a cosmological simulation is an expensive, high-dimensional parameter optimization task. Previous works employ Bayesian optimization for automation, which treats the simulator as a black box and precludes the incorporation of human domain knowledge or workflow into the selection policy. We propose AgenticTuner, an agentic calibration pipeline with a present-day large language model serving as the optimizer who proposes the next parameter trial. We show that these agents can achieve competitive calibration performance at a fraction of the CPU cost when they are given informal, human-readable priors (such as codebase, documentation, and heuristic guides that seasoned scientists may possess). We hope this work serves as an early step toward AI scientists that can carry out complex, long-horizon scientific tasks.
Related
- CosmoDyn: a semi-analytic post-processing framework for the dynamical evolution of compact stellar systems and black holes in cosmological simulations
- Rates of tidal disruption events from constrained cosmological simulations of the local Universe: population properties and implications for transient surveys
- Coupling between stellar and HI lopsidedness in Milky Way--type galaxies from the Auriga Superstars cosmological simulations
- Bridging perturbation theory and simulations: initial conditions and fast integrators for cosmological simulations
- OpenCosmo: Community Portal and Analysis Framework for Flagship Cosmological Simulations
BibTeX
@misc{tirapongprasert2026agentic,
title = {{Agentic Systems for Calibrating Cosmological Simulations}},
author = {Chaipat Tirapongprasert and Matthew Ho},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40685},
eprint = {2610.40685},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40685},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic Systems for Calibrating Cosmological Simulations
AU - Chaipat Tirapongprasert
AU - Matthew Ho
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.40685
UR - https://arxiv.org/abs/2610.40685
AB - Calibrating a cosmological simulation is an expensive, high-dimensional parameter optimization task. Previous works employ Bayesian optimization for automation, which treats the simulator as a black box and precludes the incorporation of human domain knowledge or workflow into the selection policy. We propose AgenticTuner, an agentic calibration pipeline with a present-day large language model serving as the optimizer who proposes the next parameter trial. We show that these agents can achieve competitive calibration performance at a fraction of the CPU cost when they are given informal, human-readable priors (such as codebase, documentation, and heuristic guides that seasoned scientists may possess). We hope this work serves as an early step toward AI scientists that can carry out complex, long-horizon scientific tasks.
ER -