arXiv cs.AI· Francisco Pereira, Justine Sherry, Pratiksha Thaker·· 11 小时前AI 评分31
用智能体大语言模型实现 Knowledge Plane
Instantiating the Knowledge Plane
AI 导读
论文主张智能体大语言模型（agentic LLM）可解锁 Clark 等人 2003 年提出的 Knowledge Plane 构想，让跨管理域的互联网协同管理成为可能。作者指出当年技术缺少推理与非结构化通信两项能力，导致自动化网络管理长期局限于单一域、域间问题仍靠人工电话协调。文章聚焦这一去中心化、多智能体、竞合场景下的新研究问题，已被 HotNets '26 接收。
正文 · 原文
Abstract:In 2003, Clark et al. proposed the "Knowledge Plane", a layer of intelligent agents that share rich information about network state in order to collaboratively manage the Internet across administrative boundaries. The technology of the day lacked the two capabilities it demanded most: reasoning and unstructured communication. Thus, automated network management has remained largely confined to single domains, while interdomain problems are still resolved by human operators on the phone. We argue that agentic large language models can finally unlock the potential of the Knowledge Plane, but that doing so will require solving new research problems that arise particularly in this decentralized, multi-agent, coopetitive setting that have received limited attention in the literature thus far.
| Comments: | Accepted at HotNets '26 (Salt Lake City, UT, USA). 11 pages |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07827 [cs.NI] |
| (or arXiv:2611.07827v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07827 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1145/3847290.3859939
DOI(s) linking to related resources |
Submission history
From: Francisco Pereira [view email]
[v1]
Thu, 5 Nov 2026 11:09:21 UTC (1,482 KB)
来源：arXiv cs.AI · arxiv.org