Google Research·· 2026-06-05
Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
AI summary
Google launched a public preview of Agentic RAG-powered cross-corpus retrieval on Gemini Enterprise Agent Platform. Roles including Orchestrator, Planner, Query Rewriter, Search Fanout and Sufficient Context Agent collaborate on multi-source, multi-hop queries.
Selection record
Threshold 60Official, first-handFirst 62Second 62
AdmittedSum of both 124 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：介绍Gemini Agentic RAG多智能体检索框架
- Why it was chosen
- The complete multi-agent RAG workflow and cross-corpus evaluation data outline implementation approaches for complex multi-hop queries.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google