Dex Horthy 谈子智能体滥用：并行堆叠替代了上下文管理

Anthropic 现在建议企业从他们的 AI 系统中移除不必要的子智能体。 这是智能体架构上一次相当重大的转变，他们的团队发现，一个配备技能（Skills）的单一智能体往往能胜过复杂的多智能体系统，并且有一位客户实现了大约 2 倍的执行速度提升。 正在形成的经验法则： → 技能（Skills）：教会智能体如何做某件事，包括流程、专业知识和指令。 → 工具 / MCP：赋予智能体通过 API、操作和实时数据去做事的能力。 → 子智能体：用于并行工作、隔离上下文，或单一智能体难以处理的任务。 有意思的部分是渐进式披露。与其生成专门的智能体或把所有内容都塞进一个巨大的提示词中，不如让一个智能体按需发现并加载技能和工具。 他们的建议是：把现有的子智能体并入主循环，把它们的指令转化为技能，把它们的操作暴露为工具，并运行评估以检验性能是否依然保持。 随着模型变得越来越聪明，改进智能体架构越来越不在于你能添加什么，而在于你能删除什么。 https://t.co/DNq60Skkmc

查看原文

Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems. This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution. The emerging rules of thumb: → Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions. → Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data. → Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with. The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed. Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up. As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete. https://t.co/DNq60Skkmc