{
  "id": 6630,
  "url": "https://arxiv.org/abs/2604.16394v1",
  "title": "A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search",
  "summary": "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 r",
  "authors": "Riccardo Terrenzi, Phongsakon Mark Konrad, Tim Lukas Adam, Serkan Ayvaz",
  "category": "research",
  "topics": "agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-28T22:56:57.000Z",
  "fetched_at": "2026-07-14T16:32:37.310Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6630",
  "original_url": "https://arxiv.org/abs/2604.16394v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}