Scaling agent swarms 10x yields only 3-5x the gain of 10x more tokens for one agent
tobyordoxford · x · 2026-09-22
Toby Ord estimates that scaling a swarm by 10x delivers only 10^λ — about 3x to 5x — of the performance gain from using 10x more tokens with a single agent. With λ estimated, one can convert between swarm scaling and scaling thinking duration, suggesting extending a single agent's thinking is far more efficient than adding agents.
More from Research
- Training on production traces: single-trajectory RL may unlock continual learning — rhythmrg · 2026-09-22
- Most compute now goes to RL, letting models surpass human data limits — MarvinTBaumann · 2026-09-22
- TinyTorch: PyTorch's free curriculum to build an ML framework from scratch in 20 modules — PyTorch · 2026-09-22
- Why AI won't boost paper output for researchers who chase hard problems — kfountou · 2026-09-22
- ICML 2027 braces for 100k submissions as AI paper boom continues — CharlotteHase · 2026-09-22
- 1080 Ti beats RTX 6000 by 2.4x on dense-model inference despite 4x less bandwidth — EAccelerate_42 · 2026-09-22