Preprint · 2026 · Open access

Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist

Akshay Kumar Jagadish, Younes Strittmatter, Nori Jacoby, George Kachergis, Eric Schulz, Nathaniel D. Daw, Suyog Chandramouli, Thomas L. Griffiths

arXiv (Cornell University) · Published 24 June 2026 · DOI 10.48550/arxiv.2606.26448

Open PDFView at the publisherCite this paper

In brief

“Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist” is a 2026 preprint by Akshay Kumar Jagadish and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 13 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
13
Most cited in
2026 (12)
References
59
Authors
8

Abstract

Across the sciences, autonomous systems are increasingly being used in closed-loop discovery, proposing new theories and designing and running experiments to test them. This approach is yet to be applied in the field of cognitive science, where the central bottleneck is theory-building: the creative step of turning the accumulated failures of existing models into better ones. Theory generation has remained manual even as data collection, modeling, and experiment design have been automated. We present the Automated Cognitive Scientist (AutoCog), a fully autonomous agentic-AI system that closes this loop. Large-language-model agents advocate competing theories, each expressed as an executable cognitive model, design experiments that best discriminate them, collect behavioral data from participants recruited online, score theories against collected data based on their generative performance, diagnose why they fail, and synthesize a better successor. Repeating this cycle allows them to search the space of theories, models, and experiments. In the domain of decision-making, AutoCog recovered known decision-making strategies from simulated behavior, including unconventional ones, showing that its discoveries are ultimately driven by the data rather than strictly bound by the priors of the underlying language models. When run with human participants, it produced theories that outperformed the established theories it was seeded with and generalized to held-out studies in two different experimental settings. It also surfaced a novel theory of multi-cue decision-making in which choices show diminishing sensitivity to feature values. The distinctive predictions of this theory were confirmed in a preregistered study with new participants. AutoCog demonstrates how an automated discovery system can be used to turn cognitive theory-building into an explicit, executable, and cumulative science.

Cite this paper

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

APA 7

Jagadish, A. K., Strittmatter, Y., Jacoby, N., Kachergis, G., Schulz, E., Daw, N. D., Chandramouli, S., & Griffiths, T. L. (2026). Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26448

MLA 9

Jagadish, Akshay Kumar, et al. “Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.26448.

Chicago

Jagadish, Akshay Kumar, Younes Strittmatter, Nori Jacoby, George Kachergis, Eric Schulz, Nathaniel D. Daw, Suyog Chandramouli, and Thomas L. Griffiths. 2026. “Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26448.

Harvard

Jagadish, A. K. et al. (2026) ‘Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist’, arXiv (Cornell University). doi:10.48550/arxiv.2606.26448.

IEEE

A. K. Jagadish et al., “Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.26448.

BibTeX

@misc{jagadish2026closing,
  title     = {{Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist}},
  author    = {Jagadish, Akshay Kumar and Strittmatter, Younes and Jacoby, Nori and Kachergis, George and Schulz, Eric and Daw, Nathaniel D. and Chandramouli, Suyog and Griffiths, Thomas L.},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2606.26448},
  url       = {https://doi.org/10.48550/arxiv.2606.26448}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning

  • agentic AI
  • LLM agents
  • cognitive models
  • decision-making
  • generative models
  • cumulative science

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?

Jagadish, A. K., Strittmatter, Y., Jacoby, N., Kachergis, G., Schulz, E., Daw, N. D., Chandramouli, S., & Griffiths, T. L. (2026). Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26448

How many times has this paper been cited?

13 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Akshay Kumar Jagadish, Younes Strittmatter, Nori Jacoby, George Kachergis, Eric Schulz, Nathaniel D. Daw, Suyog Chandramouli, Thomas L. Griffiths.

What is the DOI of this paper?

10.48550/arxiv.2606.26448, permanently at https://doi.org/10.48550/arxiv.2606.26448. 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.