Agents
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single var…
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single variants (see also: @/karpathy’s LLM Council). Can outperform b
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single variants (see also: @/karpathy’s LLM Council). Can outperform best-of-N on accuracy but at lower cost & latency. Here’s how each method did on BrowseComp-Plus: https://www.ai21.com/blog/maestro-deep-research-agents/?utm_source=org-twitter
Source: AI21 Labs (X) | 2026-05-13