Agentic research is oxymoronic

arXiv:2608.31161 · astro-ph.IM, astro-ph.CO · Submitted 2026-08-31 · Read on arXiv

astro-ph.IM, astro-ph.CO

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 3 pages, no figures. Published as a Comment in Nature Astronomy

DOI: 10.1038/s41550-026-02954-y

License: http://creativecommons.org/licenses/by/4.0/

The gist: The use of agentic large language models obviates human interpretation of scientific results, and will lead to substantial distrust in the literature.

Terminology

• Agentic AI — 4× in this paper · explained in 1 episode
• Agentic System — 4× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Abstract

Sources

• Why do we do astrophysics?

Related papers

• A signal dedispersion algorithm for imaging-based transient searches
• EXPO: a quantum leap in fast, wide-band X-ray polarimetry for astrophysics
• CHRONOS Science Program
• AVICA: A fully automated CASA pipeline for large volume VLBI data calibration
• Spectral Map Making with SPHEREx
• Long-Integration Magnetar Burst Observatory (LIMBO): Instrument Summary and Early FRB Rate Constraints