AI RESEARCH
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
arXiv CS.AI
•
ArXi:2604.27221v1 Announce Type: new Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We