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 |

在设计多代理系统、实施主管模式、协调多个代理或询问“多代理”、“主管模式”、“群”、“代理切换”、“编排”、“并行代理”时使用 来源：eyadsibai/ltk。

查看原文