阿斯塔纳时间
AI QAZAQSTANKZ · AI测试版

哈萨克斯坦人工智能与高科技领域的智能门户

Research1 分钟阅读

内容来自原始来源:

arXiv — cs.AI

在 arXiv — cs.AI 阅读全文

本内容来自公开来源。若发布内容影响您的权利 → 申请删除信息

标题为英语Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System

An agentic system issues several structurally different kinds of LLM calls. It routes intent, classifies actions, grounds language in a device registry, plans multi-agent pipelines and writes the Python code those pipelines run. The difficulty of these call sites varies by an…

arXiv — cs.AI作者: Panagiotis Kasnesis, Christos Chatzigeorgiou, Lazaros Toumanidis, Amalia Contiero Syropoulou2026年10月8日 (10月8日)
提供 1 种语言版本

AI 摘要:要点

  • An agentic system issues several structurally different kinds of LLM calls
  • It routes intent, classifies actions, grounds language in a device registry, plans multi-agent pipelines and writes the Python code those pipelines run
  • The difficulty of these call sites varies by an…
Research
KZ·AI CD3A
Инсайт дня

Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System

标签:#arXiv
Поделиться:

相关文章

返回列表