AI scientists produce results without reasoning scientifically

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ríos-García, Martiño, Alampara, Nawaf, Gupta, Chandan, Mandal, Indrajeet, Mannan, Sajid, Aghajani, Ali Asghar, Krishnan, N. M. Anoop, Jablonka, Kevin Maik
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911609080774656
author Ríos-García, Martiño
Alampara, Nawaf
Gupta, Chandan
Mandal, Indrajeet
Mannan, Sajid
Aghajani, Ali Asghar
Krishnan, N. M. Anoop
Jablonka, Kevin Maik
author_facet Ríos-García, Martiño
Alampara, Nawaf
Gupta, Chandan
Mandal, Indrajeet
Mannan, Sajid
Aghajani, Ali Asghar
Krishnan, N. M. Anoop
Jablonka, Kevin Maik
contents Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make scientific inquiry self-correcting is poorly understood. Here, we evaluate LLM-based scientific agents across eight domains, spanning workflow execution to hypothesis-driven inquiry, through more than 25,000 agent runs and two complementary lenses: (i) a systematic performance analysis that decomposes the contributions of the base model and the agent scaffold, and (ii) a behavioral analysis of the epistemological structure of agent reasoning. We observe that the base model is the primary determinant of both performance and behavior, accounting for 41.4% of explained variance versus 1.5% for the scaffold. Across all configurations, evidence is ignored in 68% of traces, refutation-driven belief revision occurs in 26%, and convergent multi-test evidence is rare. The same reasoning pattern appears whether the agent executes a computational workflow or conducts hypothesis-driven inquiry. They persist even when agents receive near-complete successful reasoning trajectories as context, and the resulting unreliability compounds across repeated trials in epistemically demanding domains. Thus, current LLM-based agents execute scientific workflows but do not exhibit the epistemic patterns that characterize scientific reasoning. Outcome-based evaluation cannot detect these failures, and scaffold engineering alone cannot repair them. Until reasoning itself becomes a training target, the scientific knowledge produced by such agents cannot be justified by the process that generated it.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18805
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AI scientists produce results without reasoning scientifically
Ríos-García, Martiño
Alampara, Nawaf
Gupta, Chandan
Mandal, Indrajeet
Mannan, Sajid
Aghajani, Ali Asghar
Krishnan, N. M. Anoop
Jablonka, Kevin Maik
Artificial Intelligence
Materials Science
Machine Learning
Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make scientific inquiry self-correcting is poorly understood. Here, we evaluate LLM-based scientific agents across eight domains, spanning workflow execution to hypothesis-driven inquiry, through more than 25,000 agent runs and two complementary lenses: (i) a systematic performance analysis that decomposes the contributions of the base model and the agent scaffold, and (ii) a behavioral analysis of the epistemological structure of agent reasoning. We observe that the base model is the primary determinant of both performance and behavior, accounting for 41.4% of explained variance versus 1.5% for the scaffold. Across all configurations, evidence is ignored in 68% of traces, refutation-driven belief revision occurs in 26%, and convergent multi-test evidence is rare. The same reasoning pattern appears whether the agent executes a computational workflow or conducts hypothesis-driven inquiry. They persist even when agents receive near-complete successful reasoning trajectories as context, and the resulting unreliability compounds across repeated trials in epistemically demanding domains. Thus, current LLM-based agents execute scientific workflows but do not exhibit the epistemic patterns that characterize scientific reasoning. Outcome-based evaluation cannot detect these failures, and scaffold engineering alone cannot repair them. Until reasoning itself becomes a training target, the scientific knowledge produced by such agents cannot be justified by the process that generated it.
title AI scientists produce results without reasoning scientifically
topic Artificial Intelligence
Materials Science
Machine Learning
url https://arxiv.org/abs/2604.18805