Microsoft 上下文引导的多轮 Agent 模型路由研究
Microsoft 论文提出在多轮 Agent 场景按用户轮次做成本感知模型路由，让路由器读取会话历史，在零样本多轮 spreadsheet agent 测试中，同等 offloading 率下比只看当前请求的路由器多通过 3.3 分任务。
Interesting paper from Microsoft on context-guided model routing.
They found a nice trick to achieve cost-aware model routing for agents in a multi-turn setting at the user-turn level.
If you route agent turns between a cheap model and an expensive one, they suggest giving the router the session history.
Microsoft tested zero-shot routing on multi-turn spreadsheet agents.
At the same offloading rate, a router that reads the history passes 3.3 points more tasks than one that sees only the current request.
Prompt caching adds a cost to every switch. Switching from the expensive model to the cheap one recovers its cache cost within two calls. Switching up did not break even in their tests.
The cheap model's cost advantage also shrank from 6.8x to 3.2x on longer sessions.
arxiv.org/abs/2610.19292
Chat with Paper: academy.dair.ai/papers/whose…
来源：dair_ai · x.com