微软论文提出上下文引导的模型路由:在多轮智能体场景中,把会话历史交给路由器,让它在便宜与昂贵模型间按用户轮次分配任务。相同卸载率下,读取历史的零样本路由器比只看当前请求的多完成 3.3 个百分点的任务。Prompt 缓存使每次切换产生成本,从贵模型切到便宜模型两次调用即可回本,反向切换则未能回本;长会话中便宜模型的成本优势也从 6.8x 缩至 3.2x。
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.
https://arxiv.org/abs/2610.19292
Chat with Paper: https://academy.dair.ai/papers/whose-turn-is-it-context-guided-model-routing-for-stateful-agents-2610.19292
来源:DAIR.AI · x.com