跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

multi-agent-patterns

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

shipshitdev · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add shipshitdev/skills --skill multi-agent-patterns

技能说明


name: multi-agent-patterns description: Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality. metadata: version: "2.1.1" source: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/multi-agent-patterns/SKILL.md upstream_repo: muratcankoylan/Agent-Skills-for-Context-Engineering upstream_ref: main upstream_commit: 25e1fa79a33f last_synced: "2026-06-13" license: MIT tags: "multi-agent, architecture, agents"

Multi-Agent Architecture Patterns

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

When to Activate

  • Single-agent context limits constrain task complexity
  • Tasks decompose naturally into parallel subtasks
  • Different subtasks require different tool sets or system prompts
  • Building systems that must handle multiple domains simultaneously
  • Scaling agent capabilities beyond single-context limits
  • Designing production agent systems with multiple specialized components

Do not activate this skill for adjacent work owned by other skills:

  • Designing the tools each agent exposes: tool-design.

Core Concepts

Use multi-agent patterns when a single agent's context window cannot hold all task-relevant information. Context isolation is the primary benefit — each agent operates in a clean context without accumulated noise from other subtasks, preventing the telephone game problem where information degrades through repeated summarization.

Choose among three dominant patterns based on coordination needs, not organizational metaphor:

  • Supervisor/orchestrator — Use for centralized control when tasks have clear decomposition and human oversight matters. A single coordinator delegates to specialists and synthesizes results.
  • Peer-to-peer/swarm — Use for flexible exploration when rigid planning is counterproductive. Any agent can transfer control to any other through explicit handoff mechanisms.
  • Hierarchical — Use for large-scale projects with layered abstraction (strategy, planning, execution). Each layer operates at a different level of detail with its own context structure.

Design every multi-agent system around explicit coordination protocols, consensus mechanisms that resist sycophancy, and failure handling that prevents error propagation cascades.

Detailed Topics

Why Multi-Agent Architectures

The Context Bottleneck Reach for multi-agent architectures when a single agent's context fills with accumulated history, retrieved documents, and tool outputs to the point where performance degrades. Recognize three degradation signals: the lost-in-middle effect (attention weakens for mid-context content), attention scarcity (too many competing items), and context poisoning (irrelevant content displaces useful content).

Partition work across multiple context windows so each agent operates in a clean context focused on its subtask. Aggregate results at a coordination layer without any single context bearing the full burden.

The Token Economics Reality Budget for substantially higher token costs. Production data shows multi-agent systems can cost far more tokens than single-agent chat (claim-multi-agent-token-multiplier):

ArchitectureToken MultiplierUse Case
Single agent chatBaselineSimple queries
Single agent with toolsHigher than baselineTool-using tasks
Multi-agent systemMuch higher than baselineComplex research/coordination

Browsing-agent evaluation research suggests token usage, tool calls, and model choice dominate performance variance (claim-evaluation-browsecomp-variance). This supports measuring multi-agent setups against single-agent baselines instead of assuming extra agents help.

Prioritize model selection alongside architecture design — upgrading to better models often provides larger performance gains than doubling token budgets. BrowseComp data shows that model quality improvements frequently outperform raw token increases. Treat model selection and multi-agent architecture as complementary strategies.

The Parallelization Argument Assign parallelizable subtasks to dedicated agents with fresh contexts rather than processing them sequentially in a single agent. A research task requiring searches across multiple independent sources, analysis of different documents, or comparison of competing approaches benefits from parallel execution. Total real-world time approaches the duration of the longest subtask rather than the sum of all subtasks.

The Specialization Argument Configure each agent with only the system prompt, tools, and context it needs for its specific subtask. A general-purpose agent must carry all possible configurations in context, diluting attention. Specialized agents carry only what they need, operating with lean context optimized for their domain. Route from a coordinator to specialized agents to achieve specialization without combinatorial explosion.

Architectural Patterns

Pattern 1: Supervisor/Orchestrator Deploy a central agent that maintains global state and trajectory, decomposes user objectives into subtasks, and routes to appropriate workers.

User Query -> Supervisor -> [Specialist, Specialist, Specialist] -> Aggregation -> Final Output

Choose this pattern when: tasks have clear decomposition, coordination across domains is needed, or human oversight is important.

Expect these trade-offs: strict workflow control and easier human-in-the-loop interventions, but the supervisor context becomes a bottleneck, supervisor failures cascade to all workers, and the "telephone game" problem emerges where supervisors paraphrase sub-agent re

阅读完整来源 ↗