---
id: 20260613-T0-04
title: "ToolSense：LLM工具知识审计框架"
title_en: "ToolSense: LLM Tool Knowledge Audit Framework"
url: https://ai.daily.yangsir.net/daily/20260613-T0-04
issue_date: 2026-06-13
publish_date: 2026-06-12T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2606.12451
---

# ToolSense：LLM工具知识审计框架

斯坦福等机构研究人员提出ToolSense框架，用于审计大模型在大型工具目录中的参数化知识检索能力。研究发现现有嵌入检索方法可能无法充分捕捉专业工具语义，导致检索瓶颈。

## English Version

**ToolSense: LLM Tool Knowledge Audit Framework**

Researchers from Stanford and others proposed ToolSense, a framework for auditing LLMs' parametric tool retrieval capabilities over large catalogs. The study finds that existing embedding-based approaches may under-capture specialized tool semantics, causing retrieval bottlenecks.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2606.12451)

**详情页**：https://ai.daily.yangsir.net/daily/20260613-T0-04

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*