主动型智能体带来新的上下文工程挑战
LangChain Blog 的评论文章称,智能体架构正逐渐收敛为在沙箱中运行、循环调用工具的 LLM,并以 Claude Code 和 Deep Agents 为例。作者根据与智能体开发者的交流指出,主动、持续运行且面向目标的智能体带来了涉及通知节奏、记忆、异步执行、目标跟踪、对齐和浏览器操作的开放上下文工程问题。作者称,包括 LangChain 在内的业界尚未必已找到这些问题的通用解决方案。
文章将编码智能体中相对标准化的上下文工程实践——例如总结长对话、卸载大型工具调用结果和使用子智能体——与主动型智能体带来的新挑战进行了对照。
It feels like everyone is converging on the same agent architecture: an LLM, running in a loop, calling tools, running in a sandbox. Claude Code - perhaps the first high profile manifestation of this - came out over a year and a half ago. Deep Agents, our agent harness, launched over a year ago. This pattern has been building for a while.
There’s nothing bad with that convergence per se, but it has led to a sentiment among some AI engineers that I’ve talked to recently that “all the hard problems are solved” or “there’s no new AI engineering problems to solve”.
When people express this sentiment, I think they are largely talking about the context engineering practices we do to make agents work. And to some extent they are right - there are a lot of standard-ish context engineering solutions we’ve all arrived at:
- Summarizing long threads when it gets to be too much for the context window
- Offloading large tool call results
- Skills for progressive disclosure
- Tool search to deal with a lot of tools
- Subagents for context isolation
- Bash as a primary tool