Auto-Psych: AI Agents Automate Psychological Theory Discovery and Experimentation.

Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, Michael Y. Li, Noah D. Goodman, Michael C. Frank· June 26, 2026 View original

▶ The 2-minute explainer

Summary

Auto-psych is an agent-based system that automates the scientific process in computational cognitive science, generating hypotheses, designing experiments, and collecting human data via crowdsourcing to discover theories of human behavior. It successfully recovers ground-truth theories and outperforms human-generated theories in specific cognitive tasks.

Researchers have developed "auto-psych," an innovative agent-based system designed to automate the scientific discovery process within computational cognitive science. This system leverages AI agents to perform tasks traditionally handled by human researchers, including generating theoretical hypotheses, designing experimental protocols, and analyzing collected data. A significant bottleneck in scientific automation, data collection, is addressed by auto-psych through its integration with crowdsourcing platforms. This allows the system to independently launch and gather human behavioral data at scale, enabling rapid iteration and testing of theories. As a proof of concept, auto-psych was applied to a classic psychology problem: how humans judge randomness in coin flip sequences. The system demonstrated its capability to reliably recover known theories from synthetic data and, remarkably, generated theories that provided a better fit to human experimental data than those derived from existing scientific literature. This highlights the potential for AI to accelerate and enhance scientific discovery.

Why it matters

This system demonstrates a powerful new paradigm for scientific discovery, potentially accelerating research in cognitive science and other fields by automating hypothesis generation, experimentation, and data analysis. It could lead to faster development of more accurate models of human behavior.

How to implement this in your domain

  1. 1Explore integrating agent-based systems for hypothesis generation and experimental design in your research domain.
  2. 2Leverage crowdsourcing platforms for automated, scalable data collection in behavioral or social science experiments.
  3. 3Develop nested agent loops to refine theories and experimental designs iteratively.
  4. 4Apply similar automated discovery techniques to other scientific fields where theories can be represented computationally.
  5. 5Collaborate with AI researchers to adapt and deploy such systems for specific scientific challenges.

Who benefits

AcademiaAI ResearchMarket ResearchPsychologyHuman Resources

Key takeaways

  • Auto-psych automates theory discovery and experimentation in cognitive science using AI agents.
  • It integrates crowdsourcing for scalable human data collection.
  • The system successfully recovers ground-truth theories and outperforms human-generated ones.
  • This approach has the potential to significantly accelerate scientific research.

Original post by Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, Michael Y. Li, Noah D. Goodman, Michael C. Frank

"arXiv:2606.26460v1 Announce Type: new 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 cog…"

View on X

Originally posted by Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft, Linas Nasvytis, Michael Y. Li, Noah D. Goodman, Michael C. Frank on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses