Google Research· ResearchResearch paper

Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG

Google Research introduces a new agentic RAG framework that breaks down complex enterprise queries, iteratively searches for sufficient context, and includes a Sufficient Context Agent to ensure completeness before generating a response. Compared to standard RAG, it increases accuracy on factuality datasets by up to 34% and improves grounding and reasoning accuracy on domain-specific tasks. The framework is hosted on the Gemini Enterprise Agent Platform as Cross-Corpus Retrieval powered by Agentic RAG.

From the source

we introduce our new agentic RAG framework. Based on a collaboration between Google Research and Google Cloud, our multi-agent workflow goes beyond standard RAG by breaking down complex enterprise queries and iteratively searching for sufficient context before generating dependable responses.

research.google

Announced