Sequential test-time scaling beats parallel multi-agent scaling at equal budget, data shows

eliebakouch · x · 2026-09-18

Researcher Elie Bakouch shares data showing that as agent count grows, parallel test-time scaling is less efficient than sequential scaling at a similar budget (while adding latency)—and that's just going from 1 to 5 agents. Responding to claims that a proof required parallel scaling to 10,000 agents, he argues it's uncertain a 100–1000 agent swarm might have sufficed, and that sequential test-time compute matters far less than the model gap between generations (e.g. astra vs predecessors).

Related event: Researchers Debate Whether 10,000-Agent Parallel Scaling Was Key to Navier-Stokes Proof(8 posts)→

Original post →

More from Research

Research channel →