Journal article · 2026 · Open access

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

Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason M. Tangen, Jason B. Mattingley, Shane E. Ehrhardt

Advanced Science, 13(56), e76675 · Published 14 September 2026 · DOI 10.1002/advs.76675

Open PDFView at the publisherCite this paper

In brief

“Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants” is a 2026 journal article by Gabrielle Wehr and 6 co-authors, published in Advanced Science. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Advanced Science.

Citations
0
References
229
Authors
7

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wehr, G., Rideaux, R., Fox, A. J., Lightfoot, D. R., Tangen, J. M., Mattingley, J. B., & Ehrhardt, S. E. (2026). Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants. Advanced Science, 13(56), e76675. https://doi.org/10.1002/advs.76675

MLA 9

Wehr, Gabrielle, et al. “Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants.” Advanced Science, vol. 13, no. 56, 2026, p. e76675. https://doi.org/10.1002/advs.76675.

Chicago

Wehr, Gabrielle, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason M. Tangen, Jason B. Mattingley, and Shane E. Ehrhardt. 2026. “Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants.” Advanced Science 13 (56): e76675. https://doi.org/10.1002/advs.76675.

Harvard

Wehr, G. et al. (2026) ‘Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants’, Advanced Science, 13(56), p. e76675. doi:10.1002/advs.76675.

IEEE

G. Wehr et al., “Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants,” Advanced Science, vol. 13, no. 56, p. e76675, 2026, doi: 10.1002/advs.76675.

BibTeX

@article{wehr2026closing,
  title     = {{Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants}},
  author    = {Wehr, Gabrielle and Rideaux, Reuben and Fox, Amaya J. and Lightfoot, David R. and Tangen, Jason M. and Mattingley, Jason B. and Ehrhardt, Shane E.},
  journal   = {Advanced Science},
  year      = {2026},
  volume    = {13},
  number    = {56},
  pages     = {e76675},
  doi       = {10.1002/advs.76675},
  url       = {https://doi.org/10.1002/advs.76675}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications

  • agentic AI
  • AI scientists
  • autonomous research
  • hypothesis generation
  • manuscript preparation
  • visual working memory
  • mental rotation
  • imagery vividness

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wehr, G., Rideaux, R., Fox, A. J., Lightfoot, D. R., Tangen, J. M., Mattingley, J. B., & Ehrhardt, S. E. (2026). Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants. Advanced Science, 13(56), e76675. https://doi.org/10.1002/advs.76675

How many times has this paper been cited?

0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Advanced Science: sign in and open the PDF from this page.

Who wrote this paper?

Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason M. Tangen, Jason B. Mattingley, Shane E. Ehrhardt.

What is the DOI of this paper?

10.1002/advs.76675, permanently at https://doi.org/10.1002/advs.76675. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.