causal

Multi-agent coordination hurt by reasoning-flow interruptions

Early multi-agent attempts were difficult because reasoning models were trained to think alone; constant checking in with or receiving messages from other agents interrupts chain of thought, creating an optimization problem, which improves as models become more general.

causalpending

Speaker

Noam Brown

Evidence Quote

“they’re in this local minimum where they’re really good at thinking deeply about a problem, and it just interrupts their chain of thought.”

Source

Dwarkesh Patel Podcast - Noam Brown – Agent swarms, alignment, & recursive self-improvement— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:12:01 AM

Your notes

Loading notes...