arXiv cs.AI· Haoran Luo, Jiapu Wang, Linhao Luo, Luu Anh Tuan·· 10 小时前AI 评分40
KnowledgeClaw:用全模态超图实现智能体知识工程
KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs
AI 导读
KnowledgeClaw 是一个构建全模态类型化超图、并通过闭环生命周期智能体保持知识库更新的智能体系统,在六项任务上均排名第一,整体 OKE 达 55.9,比最强基线高 14.6。团队同时提出 OmniKE 形式化定义并发布 OmniKE-Bench,包含六项任务、1,829 个无需模型评分的条目,覆盖五种模态的 3,960 个真实文件。软件与数据已公开。
正文 · 原文
Abstract:Knowledge engineering (KE) turns raw files into a reasoning-ready knowledge base, a task now within reach of LLM agents. KE has progressed from chunk and graph retrieval-augmented generation (RAG) to memory agents, agentic KE and multimodal KE. However, a live knowledge base needs omnimodality, a closed-loop lifecycle and multi-granular application at once, yet existing systems meet at most two and no benchmark measures all three. We formalize Omnimodal Knowledge Engineering (OmniKE) and release OmniKE-Bench, six tasks with 1,829 model-free items over 3,960 real files in five modalities. We further propose KnowledgeClaw, an agentic system that builds an omnimodal typed hypergraph, keeps it current with a closed-loop lifecycle agent and routes each query to the granularity it needs. Against 30 baselines, it ranks first on all six tasks with an overall OKE of 55.9, +14.6 over the strongest baseline. Our software and data are publicly available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24294 [cs.AI] |
| (or arXiv:2611.24294v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24294 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoran Luo [view email]
[v1]
Wed, 18 Nov 2026 12:06:06 UTC (2,499 KB)
来源:arXiv cs.AI · arxiv.org