astro-ph.IMOct 26, 2026

Agentic Systems for Calibrating Cosmological Simulations

Authors: Chaipat Tirapongprasert, Matthew Ho

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

Explore similar work

CardsList
  1. Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative

    Jul 17, 2026David Gómez-Guillén, Mireia Diaz, Josep Lluis Arcos +1Parameter EstimationBlack-Box Optimization

  2. Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology

    May 14, 2026Licong Xu, Thomas BorrettMulti-Agent LLM SystemsAI Agents for Scientific Discovery

  3. Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research

    Mar 18, 2026Thomas Borrett, Licong Xu, Andy Nilipour +7Scientific Workflow AutomationAutonomous Research Agents