benchmarks evals
Many Small Agent Teams Beat One Large Team
Sampling teams of ten balances collaboration quality with the variance benefit of repeated attempts.
Summary
Sampling teams of ten balances collaboration quality with the variance benefit of repeated attempts.
Across twelve long-horizon tasks, parallel teams of ten beat independent agents on ten tasks and a single 100-agent team on every task where that comparison ran. The result assumes a verifier can score attempts and reflects the paper’s model and task set.
Why it matters
Sampling teams of ten balances collaboration quality with the variance benefit of repeated attempts.
Limits and context
No additional limitation was separately recorded.
Key claims
Sampling teams of ten balances collaboration quality with the variance benefit of repeated attempts.
Evidence: source-2026-11-09-020
Sources
- arXiv preprint 2611.09798, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.