Most Multi-Agent Systems Should Be One Agent With Better Tools

Automated excerpt

TL;DR: Most published multi-agent wins compare a team of agents against a single agent given far less compute. Before adding an agent, give your single agent the same token budget and compare them on your own labelled cases. "Add another agent" has become the default answer to an agent that isn't good enough.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.