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 Tangen, Jason B. Mattingley, Shane E. Ehrhardt · 2026
Read Closing the Empirical Loop: Autonomous AI Agents Conduct End‐to‐end Research With Human Participants by Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason Tangen, Jason B. Mattingley, Shane E. Ehrhardt (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13573717.txt.
Description
Gabrielle Wehr and co-authors show that an autonomous AI system can run complete psychology studies with human participants, from first idea to finished manuscript. AI tools have sped up single tasks like predicting protein shapes, but they still need heavy human steering. The authors test a general system meant to work across fields on its own.
The system designed and ran three studies on visual memory, mental rotation, and the vividness of mental images. It formed the questions, recruited and ran participants, handled the data, and drafted the papers. Such end-to-end work raises hopes for faster science and hard questions about trust and credit. The demonstration is a landmark case for debate.
Catalog record
| CREATOR | Gabrielle Wehr, Reuben Rideaux, Amaya J. Fox, David R. Lightfoot, Jason Tangen, Jason B. Mattingley, Shane E. Ehrhardt |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 91 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |