OpenAI researcher Noam Brown explains sub-linear efficiency and emergent coordination in multi-agent systems
Noam Brown states multi-agent systems are essentially parallelized test-time compute with sub-linear efficiency dependent on task type; he advocates minimal built-in structure for emergent coordination but admits lack of solid measurement at 10,000-agent scale.
In a Dwarkesh Patel podcast, OpenAI researcher and o1 core author Noam Brown explained the actual operational logic of multi-agent systems. He noted that multi-agent approaches fundamentally convert test-time compute from pure serial scaling to parallel scaling. Just as giving humans five minutes versus five hours for an exam yields vastly different results, models perform better with more thinking time—but since waiting years is impractical, teams must work in parallel.
Brown emphasized inherent losses in this parallelization: multiple agents do not share full context like a single agent, reducing efficiency. Tests showed four agents working half-duration each yield answers twice as fast, while scaling to 16 follows similar patterns with slightly lower efficiency. Gains exhibit mild sub-linearity and depend heavily on the problem—math and Deep Research suit parallelization well, whereas novel writing gains little from adding agents.
Addressing attention on 10,000-agent scales, Brown admitted no solid scientific understanding exists yet. Full ablation experiments are unaffordable, so they study behavior incrementally at 64 to 256 agents. He stated clearly that solving millennium problems stems primarily from strong base models; multi-agent novelty earned disproportionate praise despite contributing less than 10%.
On architecture, Brown contrasted two approaches. Traditional methods rely heavily on scaffolds with coordinator agents assigning tasks, preventing similar-task sub-agents from communicating and forcing them to guess or return questions when clarification is needed. OpenAI chose the opposite extreme: minimal built-in structure, giving agents only primitive messaging tools where messages write directly into recipients' contexts.