Back to search

Article

On the Limits of End-to-End Foundation Models: Coordination as a Missing Primitive for Artificial General Intelligence

2026-05-22

Abstract excerpt

<title>Abstract</title> <p>We argue that scaling end-to-end foundation models alone is unlikely to yield general intelligence, as current architectures lack explicit mechanisms for coordination. We define general intelligence as the ability to flexibly coordinate perception, memory, reasoning, and action across diverse and changing tasks. Under this view, existing models rely on implicit coordination that remains...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work
6741a773-4da4-55cf-81fb-fce1e12cb589
DOI
10.21203/rs.3.rs-9784163/v1
Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
On the Limits of End-to-End Foundation Models: Coordination as a Missing Primitive for Artificial General IntelligenceDOI 10.21203/rs.3.rs-9784163/v1
Select a neighboring publication to make it the new centre.