Preprint · 2026 · Open access

auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation

Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, M. Li, Noah D. Goodman, Michael C. Frank

arXiv (Cornell University) · Published 24 June 2026 · DOI 10.48550/arxiv.2606.26460

Open PDFView at the publisherCite this paper

In brief

“auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation” is a 2026 preprint by Ben Prystawski and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 8 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
8
Most cited in
2026 (8)
References
53
Authors
7

Abstract

AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this pipeline, however. Psychology, and computational cognitive science in particular, is well-positioned to benefit from AI experimentation because theories are often represented as code and crowdsourcing platforms enable programmatic human data collection at scale. Here, we apply automated discovery techniques to the project of generating theories in computational cognitive science, with an agent-based system collecting human data independently through crowdsourced survey experiments. As a testbed, we use a classic case study from cognitive psychology: judging which sequences of coin flips seem subjectively more random. Our system, auto-psych, uses nested agent-based discovery loops to generate explanatory theories of human behavior. The inner loop conjectures, fits, and critiques probabilistic cognitive models; the outer loop designs experiments to test these models, launches them online, and analyzes the data. This system can quickly and reliably recover ground-truth theories from synthetic data via systematic experimentation, but the nested structure is critical to model performance. Further, in three independent sequences of human experiments, the system finds theories that fit the data better than theories generated from the scientific literature. This work thus demonstrates the feasibility of automated data collection and theory discovery in computational cognitive science.

Cite this paper

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

APA 7

Prystawski, B., Mukherjee, K., Wurgaft, D., Nasvytis, L., Li, M., Goodman, N. D., & Frank, M. C. (2026). auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26460

MLA 9

Prystawski, Ben, et al. “auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.26460.

Chicago

Prystawski, Ben, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, M. Li, Noah D. Goodman, and Michael C. Frank. 2026. “auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26460.

Harvard

Prystawski, B. et al. (2026) ‘auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation’, arXiv (Cornell University). doi:10.48550/arxiv.2606.26460.

IEEE

B. Prystawski et al., “auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.26460.

BibTeX

@misc{prystawski2026auto,
  title     = {{auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation}},
  author    = {Prystawski, Ben and Mukherjee, Kushin and Wurgaft, Daniel and Nasvytis, Linas and Li, M. and Goodman, Noah D. and Frank, Michael C.},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2606.26460},
  url       = {https://doi.org/10.48550/arxiv.2606.26460}
}

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

Topic and keywords

Life Sciences › Neuroscience › Cognitive Neuroscience › Cognitive Science and Education Research

  • crowdsourced data collection
  • computational cognitive science
  • hypothesis generation
  • experimental design
  • online survey experiment

Work with this paper

Most-cited papers in Neuroscience

All highly cited Neuroscience papers

Questions about this paper

How do I cite this paper in APA style?

Prystawski, B., Mukherjee, K., Wurgaft, D., Nasvytis, L., Li, M., Goodman, N. D., & Frank, M. C. (2026). auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.26460

How many times has this paper been cited?

8 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?

Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, M. Li, Noah D. Goodman, Michael C. Frank.

What is the DOI of this paper?

10.48550/arxiv.2606.26460, permanently at https://doi.org/10.48550/arxiv.2606.26460. 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.