{
  "id": 17065,
  "url": "https://arxiv.org/abs/2608.06305v1",
  "title": "Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations",
  "summary": "Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding spa",
  "authors": "Sagar Tamang, Ayush Vyas, Tabarakul Hazarika",
  "category": "research",
  "topics": "regulation,agents-autonomy,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T17:23:13.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/17065",
  "original_url": "https://arxiv.org/abs/2608.06305v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}