multi-agent-patterns

SKILL.md

Multi-agent architectures distribute work across multiple LLM instances, each with its own context window. The critical insight: sub-agents exist primarily to isolate context, not to anthropomorphize role division.

Context Bottleneck: Single agents fill context with history, documents, and tool outputs. Performance degrades via lost-in-middle effect and attention scarcity.

| Single agent chat | 1× baseline | | Single agent + tools | 4× baseline | | Multi-agent system | 15× baseline |

在設計多代理系統、實施主管模式、協調多個代理或詢問「多代理」、「主管模式」、「群組」、「代理切換」、「編排」、「並行代理」時使用 來源：eyadsibai/ltk。

查看原文