Google launches Agentic RAG framework based on Gemini Enterprise Agent Platform
Original title:Unlocking dependable responses with Gemini Enterprise Agent Platform’s Agentic RAG
AI summary
Google Research and Google Cloud jointly launched the Cross-Corpus Retrieval framework as Agentic RAG on Gemini Enterprise Agent Platform. The multi-agent workflow decomposes complex enterprise queries into subtasks, iteratively searches multiple data sources through planning, rewriting, and routing until sufficient context is obtained, then generates reliable answers. Compared with standard RAG, it improves accuracy by up to 34% on factual datasets; it also achieves better grounding and reasoning accuracy on several domain-specific internal datasets.
Key Takeaways
- Google Research and Google Cloud jointly launched the Cross-Corpus Retrieval framework as Agentic…
- The multi-agent workflow decomposes complex enterprise queries into subtasks,iteratively searches…
- Compared with standard RAG,it improves accuracy by up to 34% on factual datasets
- it also achieves better grounding and reasoning accuracy on several domain-specific internal…
Quick Facts
- Published
- Updated
- Source
- Google Research:Blog(网页)
- Category
- Products & Apps
- AI score
- 64
企业级 RAG 的新标杆,多 agent 架构加上‘足够上下文’检查,准确度提升 34%。做知识库问答的产品经理和架构师都应该认真看。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Google launches Agentic RAG framework based on Gemini Enterprise Agent Platform. June 5, 2026. https://new.nat6.net/en/news/cmq1dossi0ev7sltrrihfn7pb/