PreprintCC BY 4.0arXiv
Agentic research is oxymoronic
Abstract
The use of agentic large language models obviates human interpretation of scientific results, and will lead to substantial distrust in the literature.
Versions
Related
- Agentic Systems for Calibrating Cosmological Simulations
- The Agentic Observer Hackathon: Autonomous Decision-making in Simulated Astronomical Surveys
- An agentic framework for gravitational-wave counterpart association in the multi-messenger era
- Discovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
- Agentic AI for Gravitational Wave Data Analysis: A Head-to-Head Comparison of Coding Agents Executing a Matched Filter Pipeline on Einstein Telescope Simulated Data
BibTeX
@misc{hogg2026agentic,
title = {{Agentic research is oxymoronic}},
author = {Natalie B. Hogg},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.31161},
eprint = {2608.31161},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.31161},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Agentic research is oxymoronic
AU - Natalie B. Hogg
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.31161
UR - https://arxiv.org/abs/2608.31161
AB - The use of agentic large language models obviates human interpretation of scientific results, and will lead to substantial distrust in the literature.
ER -