Unverified90% confidenceFactTime unknown
Agentic RAG用搜索工具替代了固定流水线，让Agent自主决定是否调用搜索、何时重写查询、是否需要多轮检索
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedAgentic RAG introduces an Agent mechanism based on the ReAct (Reasoning + Acting) framework, giving the system the autonomous ability to judge whether retrieval is needed, where to retrieve from, and how to evaluate retrieval quality.79% similarUnverifiedAgentic RAG grants the model autonomous planning capability, enabling it to assess whether information is sufficient, decide whether to perform multi-round retrieval, choose which tools or data sources to invoke, and carry out self-reflection and iterative correction.78% similarUnverifiedAgentic Search 是赋予大模型工具调用能力，让模型自主决策何时搜索、搜什么以及是否充分76% similarUnverifiedThe combination of RAG and Agents is one of the mainstream solutions for current enterprise-level applications, where the Agent can proactively decide when to retrieve and execute multi-hop retrieval.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/11815API
curl https://kongchang.com/api/v1/knowledge/claims/11815MCP
get_claim(id=11815)