Metraipolis › archive › dc_2823b8d796bc

Agentic Systems for Calibrating Cosmological Simulations — arXiv:2610.40685

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40685
License (as archived)
CC0-1.0
Archived
2026-11-03T07:34:43.169Z
SHA-256 of the archived text
5b51ff676c13831de8842c6fab50f2abb84fa6849a79445c6f803219967d5630
Stable URL of this page
https://metraipolis.com/documento/dc_2823b8d796bc

How to cite

Agentic Systems for Calibrating Cosmological Simulations — arXiv:2610.40685 — arXiv (en), https://arxiv.org/abs/2610.40685 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2823b8d796bc (Metraipolis archive dc_2823b8d796bc, sha256 5b51ff676c13831de8842c6fab50f2abb84fa6849a79445c6f803219967d5630)
BibTeX
@misc{dc2823b8d796bc,
  title = {Agentic Systems for Calibrating Cosmological Simulations — arXiv:2610.40685},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40685},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2823b8d796bc; sha256 5b51ff676c13831de8842c6fab50f2abb84fa6849a79445c6f803219967d5630},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40685. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Instrumentation and Methods for Astrophysics (astro-ph.IM) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.40685 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:29:47.993Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).