More agents = more intelligence?

The Problem with Multi-Agent Orchestration

Multi-agent orchestration isn't "more powerful." It's usually a more expensive way to get worse reasoning. Every agent-to-agent handoff is a lossy compression step. The receiving agent never sees the nuance the previous one worked through - only its sanitised summary.

The Evidence

Google's own research found multi-agent coordination dropped sequential reasoning performance by 39-70%. A Sber whitepaper clocked ~15x the token usage versus single-agent chat.

When Multi-Agent Earns Its Overhead

Multi-agent earns its overhead in exactly one scenario: the work is genuinely parallel, or too large for a single context window.

The Alternative

Everything else? A single agent with good tools and enough context will out-reason your swarm - at a fraction of the cost. The "more agents = more intelligence" playbook is hype math, not engineering math.

What do you think?👇

Towards a science of scaling agent systems: When and why agent systems work
research.google AI