Agentic Systems for Calibrating Cosmological Simulations
Organizations: Columbia University · Institute for Advanced Study
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.
Figures & tables
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| Parameter | Role | Prior box |
|---|---|---|
| ( Omega0 ) | cosmological | |
| ( OmegaBaryon ) | cosmological | |
| ( Sigma8 ) | cosmological | |
| ( PrimordialIndex ) | cosmological | |
| ( HubbleParam ) | cosmological | |
| WindSigma0 | wind mass-loading | km/s |
Model Calibration
Model calibration aligns predicted confidence or model outputs with observed outcomes and measurements to support more reliable decisions.
See all 245 papersBeyond AI as Assistants: Toward Autonomous Discovery in Cosmology
CMBEvolve, which targets tasks with explicit quantitative objectives through LLM-guided code evolution and tree search, and CosmoEvolve, which targets open-ended scientific workflows through a virtual multi-agent research laboratory. As preliminary demonstrations, we apply CMBEvolve to out-of-distribution detection in weak-lensing maps, where it iteratively improves the benchmark score through code evolution, and CosmoEvolve to autonomous ACT DR6 data analysis, where it identifies non-trivial pair- and scale-dependent behaviour and produces analysis-grade diagnostics. These examples show how cosmology can provide both controlled benchmark tasks and realistic open-ended research problems for the development of AI scientist systems.