AI-augmented ACT-R modeling in real interfaces: automating visual perception, knowledge acquisition, and motor misexecution
Amirreza Bagherzadeh, Farnaz Tehranchi · 2026
Read AI-augmented ACT-R modeling in real interfaces: automating visual perception, knowledge acquisition, and motor misexecution by Amirreza Bagherzadeh, Farnaz Tehranchi (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-13625840.txt.
Description
Amirreza Bagherzadeh and Farnaz Tehranchi present a tool that helps a classic model of the human mind work on real computer screens, in a 2026 paper. The model, ACT-R, stands for a theory of how people see, know, and act. In the past, modelers had to code each screen object and each task step by hand, and the model never made mistakes with the mouse.
Their tool, EVisiTor, reads live screens and turns objects into features the model can use. It also turns plain written steps into knowledge the model can run, and it lets the model slip on actions and then catch the slip. Tested on a spreadsheet task, the model matched human times far better than a flawless-user version. It also ran six live Windows tasks from written guides.
Catalog record
| CREATOR | Amirreza Bagherzadeh, Farnaz Tehranchi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 95 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |