RESEARCHInvestigateNEXT 12 MONTHS
WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
WorkSurface-Bench is a new benchmark for enterprise agents, evaluating their ability to select and integrate knowledge from heterogeneous sources (documents, tables, graphs).
Open sourceOneBench interpretation
Institutional assessment
So what
New enterprise agent benchmark evaluates a critical capability for G-SIB knowledge routing: selecting optimal information sources.
Do what
Add WorkSurface-Bench to the Q4 model evaluation team's agentic AI review for practical applicability.