PulseAugur
实时 09:31:12
English(EN) Selection Is Retrieval, Abstention Is Not: On-Device Tool Routing over 70 Korean-English Actions

设备端AI工具路由研究强调神经弃权的需求

研究人员探索了AI助手在设备端的工具路由,区分了工具选择和弃权(当没有工具适用时)。传统的单一语言模型方法在本地设备的延迟和内存方面成本高昂。一种替代方法用检索器取代语言模型,检索器对本地操作进行排序,但无法指示何时没有合适的动作。研究发现,虽然BM25可以有效地为词汇匹配的请求选择工具,但神经组件对于准确的弃权至关重要。使用像multilingual-e5-base这样的冻结编码器仅用于弃权,可以使许多请求保持在本地,同时正确识别需要委托的请求,尽管神经排序器以增加延迟和内存为代价提高了整体质量。 AI

影响 强调了设备端AI的神经模型和检索器之间的权衡,表明神经组件是弃权的关键。

排序理由 学术论文,详细介绍了一种新颖的AI助手工具路由方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

设备端AI工具路由研究强调神经弃权的需求

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了一种新颖的AI助手工具路由方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Janghoon Lee (Redrob) ·

    选择即检索,弃权非检索:设备端工具路由处理 70 余项韩英动作

    arXiv:2609.18672v1 Announce Type: new Abstract: An AI assistant that calls tools makes two decisions on every request: which tool to invoke, and whether any available tool applies. In the usual design a single language model makes both, by emitting a call or by declining to emit …