Agentic AI Reference Architecture

Knowledge & Data · Software component

Query Rewriter

Software componentKnowledge & DataKnowledge & Dataarc:QueryRewriter

A retrieval-preparation component that reformulates a question or sub-question into a search query, incorporating intermediate answers from earlier hops.

Responsibility. Formulates retrieval queries from the current sub-question and prior intermediate results.

Also known as: Retrieval query formulation, Query expansion, Query expander

readsreadssends data tosends data tois invoked byWorking Memory Buffer: readsWorking Memory BufferConversation State Store: readsConversation State StoreVector Retriever: sends data toVector RetrieverDense-Sparse Hybrid Retriever: sends data toDense-Sparse Hybrid Retr…Multi-Hop Retrieval Controller: is invoked byMulti-Hop Retrieval Cont…
Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

reads dependency

sends data to dynamic

Design guidance

Classification

Patterns
Query formulation from intermediate resultsQuery expansionQuery decompositionCoreference resolution from conversation historyQuery expansion with synonyms and related terms
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Searching with wrong keywordsSecond-hop retrieval of documents about the wrong entityGeneric queries retrieving non-specific documents

Sources

  1. Ch3.3: T. Nguyen, "Web Navigation and Interaction Benchmarks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.3. ISBN: 9798244538229.
  2. Ch3.10: T. Nguyen, "Efficiency Metrics," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.10. ISBN: 9798244538229.
  3. Ch5.8: T. Nguyen, "Semantic Memory," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.8. ISBN: 9798244538229.