# SemiAnalysis：智能体流量已占全部推理流量 70% 以上

- 来源：SemiAnalysis (@SemiAnalysis_)
- 发布时间：2026-09-17 23:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.news/items/cmu5o4ts20djiroqok8sz12o1
- 原文链接：https://x.com/SemiAnalysis_/status/2100600804038099217

## AI 摘要

SemiAnalysis 称智能体流量现已占全部推理流量 70% 以上，并总结了智能体负载的四个特征：多轮会话带来高 KV-cache 复用潜力、系统提示词与工具定义使上下文快速累积、线性对话使多数上下文可由 KV cache 直接服务（随轮数增长缓存输入与未缓存输入之比趋于 1）、以及子智能体突发产生的短上下文突发式 KV-cache 模式。

## 正文

AGENTIC TRAFFIC NOW MAKES UP MORE THAN 70% OF ALL INFERENCE TRAFFIC 🚀

Agentic workloads are characterized by four elements:

🟠 Multi-turn: a session includes tens or hundreds of turns, leading to high potential KV-cache reuse.

🟠 Long context: system prompts, tool definitions, and the large number of turns make context accumulate quickly.

🟠 High prefix reuse: since the conversation progresses linearly, where output from turn n-1 is concatenated to turn n (typically), most context can be served from KV cache rather than recomputed (this depends on the amount of storage available to store KV tensors). As n grows, the ratio of cached input relative to uncached input typically tends towards 1.

🟠 Sub-agent bursts: a session launches multiple short-lived sub-agents with fresh context, which create bursty KV-cache patterns.