新闻
Deep Agents v0.7
LangChain · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- LangChain released Deep Agents v0.7, reducing base input tokens by 65% while maintaining performance through prompt and tool optimization.
- 为何重要
- Engineers building AI agents should care when optimizing token costs and context efficiency without sacrificing agent capability or reasoning quality.
- 注意
- TodoListMiddleware is now opt-in rather than default; some use cases like long multi-step tasks may need it re-enabled for proper performance.
收听本摘要
- agent
- token
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。