Metraipolis › archive › dc_47cd803ee15c

Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations — arXiv:2608.06305

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06305
License (as archived)
CC0-1.0
Archived
2026-10-25T21:31:29.269Z
SHA-256 of the archived text
4239c832705e418f61885c230a1db570fd3b5fa40ab7576adf9cb183c4ac9727
Stable URL of this page
https://metraipolis.com/documento/dc_47cd803ee15c

How to cite

Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations — arXiv:2608.06305 — arXiv (en), https://arxiv.org/abs/2608.06305 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47cd803ee15c (Metraipolis archive dc_47cd803ee15c, sha256 4239c832705e418f61885c230a1db570fd3b5fa40ab7576adf9cb183c4ac9727)
BibTeX
@misc{dc47cd803ee15c,
  title = {Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations — arXiv:2608.06305},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06305},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47cd803ee15c; sha256 4239c832705e418f61885c230a1db570fd3b5fa40ab7576adf9cb183c4ac9727},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06305. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 space, and a figure inherits its unit from a header a median of 13 lines above it -- so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations -- normalized lexical search, structural navigation, and bounded span reads -- exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) -- or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.06305 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.285Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).