A Reference Architecture For Agentic Hybrid Retrieval In Dataset Search

Abstract

Ad hoc dataset search requires matching underspecified natural-language queries against sparse, heterogeneous metadata records, a task where typical lexical or dense retrieval alone falls short. We reposition dataset search as a software-architecture problem and propose a bounded, auditable reference architecture for agentic hybrid retrieval that combines BM25 lexical search with dense-embedding retrieval via reciprocal rank fusion (RRF), orchestrated by a large language model (LLM) agent that repeatedly plans queries, evaluates the sufficiency of results, and reranks candidates. To reduce the vocabulary mismatch between user intent and provider-authored metadata, we introduce an offline metadata augmentation step in which an LLM generates pseudo-queries for each dataset record, augmenting both retrieval indexes before query time. Two architectural styles are examined: a single ReAct agent and a multi-agent horizontal architecture with Feedback Control. Their quality-attribute tradeoff

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyterrenzi2026a

Related papers

• DAT: Dynamic Alpha Tuning For Hybrid Retrieval In Retrieval-augmented Generation (2025)0.00
• Hetarag: Hybrid Deep Retrieval-augmented Generation Across Heterogeneous Data Stores (2025)3.27
• Advancing Retrieval-augmented Generation For Structured Enterprise And Internal Data (2025)1.20
• Domain-adaptive And Scalable Dense Retrieval For Content-based Recommendation (2026)0.00
• Utilizing Metadata For Better Retrieval-augmented Generation (2026)0.00
• Rear: Retrieve, Expand And Refine For Effective Multitable Retrieval (2025)0.00
• Searchgym: A Modular Infrastructure For Cross-platform Benchmarking And Hybrid Search Orchestration (2026)0.00
• Rethinking Hybrid Retrieval: When Small Embeddings And LLM Re-ranking Beat Bigger Models (2025)0.00