"We鈥檝e found that multi-agent systems excel at valuable tasks that involve heavy parallelization, information that exceeds single context windows, and interfacing with numerous complex tools."
"There is a downside: in practice, these architectures burn through tokens fast. In our data, agents typically use about 4脳 more tokens than chat interactions, and multi-agent systems use about 15脳 more tokens than chats"
"We found that a multi-agent system with Claude Opus 4 as the lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on our internal research eval."
Follow up to my random hot take not really thought out response of multi agent systems being overhyped and ngmi - Cognition just put this out and I like 70% agree but this is a decent framing of current issues w/ multi agent - wish it was a bit more forward thinking too but decent quick read
https://cognition.ai/blog/dont-build-multi-agents#applying-the-principles