# A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search

arXiv: https://arxiv.org/abs/2604.16394 · HTML: https://mlsanity.com/paper/2604.16394/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 28 Mar 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [An Analysis of Fusion Functions for Hybrid Retrieval](https://mlsanity.com/paper/2210.11934/) (2022)
- [RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback](https://mlsanity.com/paper/2403.06840/) (2024)
- [Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2411.19443/) (2024)
- [RAG-Fusion: a New Take on Retrieval-Augmented Generation](https://mlsanity.com/paper/2402.03367/) (2024)
- [Dataset search: a survey](https://mlsanity.com/paper/1901.00735/) (2019)
- [Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents](https://mlsanity.com/paper/2405.10467/) (2024)
- [When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail](https://mlsanity.com/paper/2601.04748/) (2026)
- [Auctus: A Dataset Search Engine for Data Augmentation](https://mlsanity.com/paper/2102.05716/) (2021)
- [LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering](https://mlsanity.com/paper/2511.13998/) (2025)
- [Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents](https://mlsanity.com/paper/2311.13148/) (2023)
- [X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System](https://mlsanity.com/paper/2505.15372/) (2025)
- [AutoDDG: Automated Dataset Description Generation using Large Language Models](https://mlsanity.com/paper/2502.01050/) (2025)
- [Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration](https://mlsanity.com/paper/2507.06520/) (2025)
- [Improving Table Retrieval with Question Generation from Partial Tables](https://mlsanity.com/paper/2508.06168/) (2025)
- [METAM: Goal-Oriented Data Discovery](https://mlsanity.com/paper/2304.09068/) (2023)
- [Blend: A Unified Data Discovery System](https://mlsanity.com/paper/2310.02656/) (2023)
- [AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents](https://mlsanity.com/paper/2510.21031/) (2025)
- [Keywords are not always the key: A metadata field analysis for natural language search on open data portals](https://mlsanity.com/paper/2509.14457/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bringing Agentic Search to Earth Observation Data Discovery](https://mlsanity.com/paper/2607.02387/) (2026)

## Abstract (arXiv)

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 tradeoffs are analyzed with respect to modifiability, observability, performance, and governance. An evaluation framework comprising seven system variants is defined to isolate the contribution of each architectural decision. The architecture is presented as an extensible reference design for the software architecture community, incorporating explicit governance tactics to bound and audit nondeterministic LLM components.