Metraipolis › archive › dc_78fe84e95e61

Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning — arXiv:2608.05757

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05757
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:12.218Z
SHA-256 of the archived text
3a696cd50ad36cd44ecbebfe9831d03306e12f7650ccf7f9e01ce34b3cfa4ed2
Stable URL of this page
https://metraipolis.com/documento/dc_78fe84e95e61

How to cite

Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning — arXiv:2608.05757 — arXiv (en), https://arxiv.org/abs/2608.05757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_78fe84e95e61 (Metraipolis archive dc_78fe84e95e61, sha256 3a696cd50ad36cd44ecbebfe9831d03306e12f7650ccf7f9e01ce34b3cfa4ed2)
BibTeX
@misc{dc78fe84e95e61,
  title = {Beyond Relevance: Bayesian Evidence Acquisition for Agentic Whole-Slide Image Reasoning — arXiv:2608.05757},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05757},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_78fe84e95e61; sha256 3a696cd50ad36cd44ecbebfe9831d03306e12f7650ccf7f9e01ce34b3cfa4ed2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-free agentic frameworks formulate this process as iterative patch retrieval based on semantic relevance to the question. However, semantic relevance does not necessarily imply diagnostic informativeness in computational pathology, where competing diagnoses often exhibit similar and overlapping morphological patterns, making many patches semantically relevant yet diagnostically non-discriminative. Consequently, relevance-based retrieval may acquire redundant observations and leave diagnostic uncertainty unresolved. We propose BEACON, a plug-and-play agentic framework that reformulates WSI reasoning as a Bayesian evidence acquisition problem. BEACON maintains a probabilistic belief over competing diagnostic hypotheses and sequentially acquires patches by maximizing expected information gain (EIG) to reduce diagnostic uncertainty. An evidence controller then determines whether to answer, acquire additional evidence, or perform higher-resolution inspection. Built entirely from off-the-shelf foundation models, BEACON requires no additional training or fine-tuning. Extensive zero-shot experiments across five WSI-VQA benchmarks demonstrate that BEACON achieves the strongest overall performance among training-free agentic frameworks while substantially improving evidence acquisition efficiency, establishing Bayesian evidence acquisition as a principled paradigm for uncertainty-aware agentic WSI reasoning. The code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05757 — 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 2026-10-31T10:23:31.010Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).