AI RESEARCH
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
arXiv CS.AI
•
ArXi:2605.29250v1 Announce Type: cross Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces.