Google Research 为 Gemini Enterprise Agent 平台加入 Agentic RAG，用 Sufficient Context Agent 处理多跳查询
Google Research Adds Agentic RAG to Gemini Enterprise Agent Platform with a Sufficient Context Agent for multi-hop queries
做企业级 AI 搜索和知识问答的团队，终于有了一个能自动补全上下文、减少幻觉的 RAG 方案——事实准确性提升 34% 不是小数字，值得点开看实现细节。
Google Research 在 Gemini Enterprise Agent 平台中引入了一种基于智能体的检索增强生成（Agentic RAG）框架，核心组件是 Sufficient Context Agent。
该智能体会自动判断当前上下文是否足够回答问题，若不足则持续检索，直到收集到足够的多源信息来回答复杂多跳查询。相比标准 RAG，该框架将事实准确性提升了高达 34%。
这一进展解决了传统 RAG 在处理需要多步推理和跨文档整合的查询时容易遗漏关键信息的问题。
Google Research Adds Agentic RAG to Gemini Enterprise Agent Platform with a Sufficient Context Agent for multi-hop queries
Google Research details an agentic RAG framework in Gemini Enterprise Agent Platform. A Sufficient Context Agent re-searches until multi-hop, multi-source queries have enough grounding to answer. The framework raises factuality accuracy up to 34% versus standard RAG. The post Google Research Adds Agentic RAG to Gemini Enterprise Agent Platform with a Sufficient Context Agent for multi-hop queries appeared first on MarkTechPost .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Key entities and technical topics under continuous tracking include Agentic RAG, Sufficient Context Agent, Gemini Enterprise Agent, 多跳查询.
Primary source verification: published directly by marktechpost with first-party authority.
