Q2D-Web tests agents on 190M documents

Q2D-Web introduces an agentic-RAG retrieval benchmark built on a 190-million-document web corpus and 70,000 search queries in 10 languages. The paper benchmarks 13 lexical, dense, and late-interaction retrievers and reports that a subcorpus containing one-third of the documents preserved full-corpus model rankings, while absolute Recall@1000 rose only 3–7 points in the full evaluation. Retrieval teams should add agent-reformulated, multilingual queries to acceptance tests rather than trust human-query leaderboards, alongside the search API cost ledger when sizing production RAG.