智能体
arxiv.org ·
知识即技能：一种用于 LLM 智能体自主使用知识库的结构化设计
该 arXiv 预印本提出 Knowledge-as-Skill 组织方案，使知识库对 LLM 智能体可发现、可导航、自描述，包含以索引为中心的发现层、每目录一个索引的导航层，以及带 YAML frontmatter（主题、类型、来源、生命周期）的知识层，遵循 Open Knowledge Format 与 Skill 协议且不修改智能体框架，并提供将 PDF、Word、网页导出与笔记转换为该结构的流水线。在 WixQA 企业客服基准的初步评测中取得 0.889 Factuality 与 0.816 Context Recall，高于所引 Corpus2Skill 的 0.767 与 0.708，但 Faithfulness 略低、Context Precision 更低、交互轮次更多；作者指出因模型、提示与知识包构建不同，结果属方向性跨工作证据而非受控对比。
AI推荐理由 arXiv 预印本，作者提出 Knowledge-as-Skill 结构化方案，让知识库对 LLM 智能体可发现、可导航、自描述，分发现层、导航层、知识层三层，遵循 OKF 与 Skill 协议且不改动智能体框架，并提供异构文档转换流水线。在 WixQA 企业客服基准上初步评测 Factuality 0.889、Context Recall 0.816，高于所引 Corpus2Skill 的 0.767 与 0.708，但 Faithfulness 略低、Context Precision 更低、交互轮次更多；作者明确说明模型、提示与知识包构建不同，属方向性跨工作证据而非受控对比。新意在于把 RAG 的检索决策权交还智能体并解决‘智能体不知道知识库有什么’的瓶颈，局限是单作者、初步评测、非受控对比，实际效果仍需验证。
72
正文
Computer Science > Information Retrieval
arXiv:2609.25991 (cs)
[Submitted on 22 Sep 2026]
Title:Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents
Authors:Jiangxu Wu
View a PDF of the paper titled Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents, by Jiangxu Wu
View PDF
HTML (experimental)
Abstract:Retrieval-augmented generation (RAG) gives large language models (LLMs) access to external knowledge, but its conventional retrieve-concatenate-generate pipeline makes retrieval decisions on behalf of the model. As tool use and agent loops become more reliable, an agent can decide whether to retrieve, what to inspect, and when to stop. This shift exposes a new bottleneck: the agent may not know what a knowledge base contains. Traditional knowledge bases expose documents as anonymous text chunks with limited information about scope, purpose, provenance, or relations.
We propose Knowledge-as-Skill, an organization scheme that makes a knowledge base discoverable, navigable, and self-descriptive. It has three layers: a discovery layer centered on this http URL; a navigation layer with one this http URL per directory; and a knowledge layer containing documents with YAML frontmatter for topic, type, provenance, and lifecycle. The design follows the Open Knowledge Format (OKF) and the Skill protocol without modifying the agent framework. We also provide knowledge-as-skill, a pipeline for converting heterogeneous collections of PDFs, Word files, web exports, and notes into this structure.
In a preliminary evaluation on the WixQA enterprise customer-support benchmark, our setup obtains 0.889 Factuality and 0.816 Context Recall, compared with reported Corpus2Skill values of 0.767 and 0.708. It obtains slightly lower Faithfulness, lower Context Precision, and more interaction turns. Because the models, prompts, and knowledge-package construction differ, these results are directional cross-work evidence rather than a controlled comparison.
Subjects:
Information Retrieval (cs.IR)
Cite as:
arXiv:2609.25991 [cs.IR]
(or
arXiv:2609.25991v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2609.25991
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiangxu Wu [view email]
[v1]
Tue, 22 Sep 2026 10:44:10 UTC (25 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Knowledge-as-Skill: A Structural Design for Autonomous Knowledge-Base Use by LLM Agents, by Jiangxu Wu
View PDF
HTML (experimental)
TeX Source
view license
Additional Features
Audio Summary
Current browse context:
cs.IR
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)