Cognition argues multi-agent architectures are fragile and proposes context-sharing principles

Cognition argues that parallel multi-agent architectures are fragile because subagents act on conflicting, unshared assumptions.

It proposes two principles for reliable agents: share context and full agent traces, and treat actions as carrying implicit decisions.

The post recommends simpler single-threaded designs for most cases and notes that context compression and fine-tuned models can extend long-running tasks.