Skip to content
Open access

Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants

Sep 2026 · Advancement of science · Vol 13 · 0 citations · 141 references
Medicine

TL;DR

It is shown that a domain‐agnostic, agentic AI Scientist system can independently navigate the scientific workflow, from hypothesis generation through data collection to manuscript preparation, a step toward embodied AI that can test hypotheses through real‐world experiments.

Abstract

ABSTRACT Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. Exponential growth of scientific literature and increasing domain specialization constrain researchers' capacity to synthesize knowledge across disciplines and develop unifying theories, motivating exploration of general‐purpose AI systems for science. Here we show that a domain‐agnostic, agentic AI Scientist system can independently navigate the scientific workflow ‐from hypothesis generation through data collection to manuscript preparation. The system autonomously designed and executed three psychological studies on visual working memory, mental rotation, and imagery vividness, executed online data collection with 288 participants, developed analysis pipelines through 8h+ continuous coding sessions, and produced completed manuscripts. The results demonstrate the capability of AI scientific discovery pipelines to conduct research with theoretical reasoning and methodological rigor comparable to experienced researchers, though with limitations in conceptual nuance and theoretical interpretation. This is a step toward embodied AI that can test hypotheses through real‐world experiments, accelerating discovery by autonomously exploring regions of scientific space that human cognitive and resource constraints might otherwise leave unexplored. It raises important questions about the nature of scientific understanding and attribution of scientific credit.

Read PDF

Similar papers

#artificial intelligence Review Open access Sep 2026

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

The introduction of ScientistTwo, a fully autonomous multi-agent framework designed to realize problem-driven autonomous research, and its results show that ScientistTwo is not merely an assistive tool but an autonomous scientific pioneer capable of pushing the frontiers of human discovery.

Jaehyun Nam, Jinsung Yoon, Yan Pan et al. · 0 citations
Open access Sep 2026

Artificial Research Intelligence

This paper explores the emergence of artificial research intelligence (ARI), autonomous AI systems designed to conduct end-to-end scientific research, from ideation to manuscript production. Unlike simple AI enhancements, ARI utilizes ensembles of agentic models to automate the scientific method, potentially creating a...

M. Ridley · 0 citations
Review Sep 2026

LLM‐Powered AI Agents in Materials Science: From Autonomous Design to Autonomous Experimentation

In this review, recent advances in material‐science agents from the complementary perspectives of autonomous design and autonomous experimentation are highlighted and a staged roadmap is proposed to facilitate the development of a standardized, reliable, and increasingly autonomous ecosystem for next‑generation materia...

Tong-Bo Jiang, Zheng-Yang Zhang, Ming-Shuo Nie et al. · 0 citations

CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition

CogGym is introduced, a scalable, unified framework grounded in cognitive science for systematically comparing model and human behavior on matched experimental trials, and intends for CogGym to provide a living evaluation framework that continually incorporates new cognitive science experiments to characterize where mo...

Lance Ying, Jin-Zhou Wu, Y. Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

It is found that predictive fit can diverge from scientific validity, memorization shapes whether models reproduce or move beyond published formulas, and the best-of-N study reveals a selection bottleneck.

Yi-Ming Huang, Zi-Chen Liu, Jun-Xia Cui et al. · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.