build1 publisher
Anthropic's Multi-Agent Research System Beat a Single Agent by 90.2%; Separately, It Uses 15x the Tokens of Plain Chat
Token use alone explained 80 percent of the variance on BrowseComp, and a Berkeley-led trace study found most multi-agent failures are structural, so the fan-out design pays only where subtasks are independent.
Publishers:dev.to
Reality
- Evidence54
- Adoption36
- Hype gap+12
- Incentives74
- Confidence55