# Duke and Princeton paper finds parallel small agent teams beat solo agents at equal compute

> Original title: New Duke and Princeton paper finds that, at equal compute, many small agent teams in parallel beat both solo-agent best-of-N and one gian...

- Source: Rohan Paul
- Published: 2026-11-10T20:02:09.000Z
- Bad Influence: https://badinfluence.news/items/sn7x3t2wne6y5x5bu46ksm8i0
- Original: https://x.com/rohanpaul_ai/status/2120245649790885952

## Summary

Duke and Princeton researchers report that, with the same budget of 100 agents, running 10 parallel teams of 10 agents and keeping the best result beat both 100 solo agents and one 100-agent team. The paper says a verifier can score each attempt, and that single large teams improve at first but stop gaining as they grow. The authors describe small teams that share notes as the way to keep many attempts while raising the average quality of each.

## Post

New Duke and Princeton paper finds that, at equal compute, many small agent teams in parallel beat both solo-agent best-of-N and one giant team.

With the same budget of 100 AI agents, running 10 small teams of 10 agents in parallel and keeping the best team’s result beat both 100 solo agents and one 100-agent team.

With a verifier, teams usually run many solo agents and keep the best, but gains flatten fast. One large team does better at first, then stops improving as it grows.

They split the agent budget into teams of 10 that share a forum, then keep the best team's result. Teamwork raises each attempt's average, and several teams still give many tries.

If a verifier can score your agents' work, split the budget into several small teams that share notes, and keep the best team's answer.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWygJznbcAAnXNy.jpg&mode=thumb&exp=1794528000&sig=e55f31da250b642f)