The Cartesian Cut in Agentic AI
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913018281984000 |
|---|---|
| author | Sainburg, Tim Weinreb, Caleb |
| author_facet | Sainburg, Tim Weinreb, Caleb |
| contents | LLMs gain competence by predicting words in human text, which often reflects how people perform tasks. Consequently, coupling an LLM to an engineered runtime turns prediction into control: outputs trigger interventions that enact goal-oriented behavior. We argue that a central design lever is where control resides in these systems. Brains embed prediction within layered feedback controllers calibrated by the consequences of action. By contrast, LLM agents implement Cartesian agency: a learned core coupled to an engineered runtime via a symbolic interface that externalizes control state and policies. The split enables bootstrapping, modularity, and governance, but can induce sensitivity and bottlenecks. We outline bounded services, Cartesian agents, and integrated agents as contrasting approaches to control that trade off autonomy, robustness, and oversight. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07745 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Cartesian Cut in Agentic AI Sainburg, Tim Weinreb, Caleb Artificial Intelligence Neurons and Cognition LLMs gain competence by predicting words in human text, which often reflects how people perform tasks. Consequently, coupling an LLM to an engineered runtime turns prediction into control: outputs trigger interventions that enact goal-oriented behavior. We argue that a central design lever is where control resides in these systems. Brains embed prediction within layered feedback controllers calibrated by the consequences of action. By contrast, LLM agents implement Cartesian agency: a learned core coupled to an engineered runtime via a symbolic interface that externalizes control state and policies. The split enables bootstrapping, modularity, and governance, but can induce sensitivity and bottlenecks. We outline bounded services, Cartesian agents, and integrated agents as contrasting approaches to control that trade off autonomy, robustness, and oversight. |
| title | The Cartesian Cut in Agentic AI |
| topic | Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2604.07745 |