KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs
This arXiv paper formalizes Omnimodal Knowledge Engineering (OmniKE), arguing that a live knowledge base needs omnimodality, a closed-loop lifecycle and multi-granular application simultaneously. It releases OmniKE-Bench, comprising six tasks with 1,829 model-free items over 3,960 real files in five modalities. The authors propose KnowledgeClaw, an agentic system that builds an omnimodal typed hypergraph, maintains it with a closed-loop lifecycle agent and routes queries to the needed granularity. KnowledgeClaw ranks first on all six tasks with an overall OKE of 55.9, reported as +14.6 over the strongest baseline, with software and data publicly available.
It offers a new benchmark and an agentic hypergraph system for knowledge engineering, giving researchers a concrete way to compare omnimodal knowledge-base approaches.
Comments & Questions (0)
No comments yet
Be the first to comment!