LangChain 创始人:多数智能体运行已不再由人类触发
LangChain 创始人放了一个很值得琢磨的数据:定时任务触发的智能体运行占比在持续上涨。如果你在做 agent 应用,该把调度和后台运行当第一优先级来设计了,而不是围着聊天框转。
LangChain 创始人 Harrison Chase 在 X 上发帖指出,当前大部分智能体(agent)运行已不是由人类手动触发,且他预计这一趋势会持续扩大。引用数据称,在被引用的一条推文中,由定时任务(schedule)启动的运行占比正随时间持续增长。
Chase 提到的核心机制是持久化智能体(persistent agents):真正有用的智能体应该按自己的节奏工作,而不是等人发出指令才运行。这意味着智能体的调度方式正从"人类发起对话"转向"系统按计划自主运行",MDA(多智能体部署)中定时触发的比例成为衡量自动化程度的一个指标。
这一判断对开发者有直接意义:构建智能体应用时需要优先考虑定时调度、后台运行和状态持久化,而不是围绕单次聊天会话设计。LangSmith 等可观测性平台也由此多了一个关键指标——按触发来源区分运行占比。
most agent runs are not triggered by humans (and i expect this trend to continue) Caspar @caspar_br Persistent agents are in We're seeing that the % of runs started by a schedule is growing with time across deployed MDAs. Useful agents work on their own time 🔗 View Quoted Tweet📊 11 ⚡
This report is categorized under AITOP's "Industry" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LangChain, agents, Harrison Chase, LangSmith.
Source attribution: curated from Harrison Chase (@hwchase17). Cross-source corroboration: 2 independent sources have covered this development (including LangChain), confirming industry-wide signal strength.
- LangChain13:23Source