Deep Agents 开源框架现在可以编程调用子代理了，还给了6种现成方案，适合搭建复杂多代理工作流。
Deep Agents 是一个开源、模型无关的代理框架。最新更新支持程序化调用子代理，并附有6种常见实现示例。博客与视频教程由 @sydneyrunkle 和 @huntlovell 提供，涵盖类似RLM的操作及代码解释器安全方案。
4/ programatic subagents in deepagents Deep Agents is our open source, model agnostic agent harness...
4/ programatic subagents in deepagents Deep Agents is our open source, model agnostic agent harness: github.com/langchain-ai/d… We added the ability to programatically call subagents. We included examples of 6 common ways to do this: - Blog: langchain.com/blog/introduci… - Video: youtu.be/5AkdMangfNk @sydneyrunkle showed how you can use this to do RLM like things: youtu.be/5_LLMZfKI6w @huntlovell wrote about how we made the code interpreter we use for this secure: langchain.com/blog/running-u… 💬 0 🔄 0 ❤️ 3 👀 359 📊 1 ⚡