Skip to content
Preprint

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

Aug 2026 · 1 citation · 33 references
Computer Science

TL;DR

BEACON is proposed, a plug-and-play agentic framework that reformulates WSI reasoning as a Bayesian evidence acquisition problem, establishing Bayesian evidence acquisition as a principled paradigm for uncertainty-aware agentic WSI reasoning.

Abstract

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 https://github.com/bryanwong17/BEACON

View source

Similar papers

#artificial intelligence Preprint Aug 2026

SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning

SlideBank is introduced, a training-free framework that represents each WSI as a persistent, concept-indexed, and spatially grounded evidence bank and achieves over 99% rephrasing consistency and substantially reduces amortized inference cost through persistent evidence reuse.

Bei-Di Zhao, Gexin Huang, Ciro Zhang et al. · 1 citation
Preprint Aug 2026

From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents

Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurrence coverage, or must discriminate competing hypotheses---which can cause failure before substantive reasoning begins. Prescribing a fine-grained solution procedure for...

Can-Can Zhang, Bao-Feng Zhang, Xiao-Tian Han et al. · 0 citations
Preprint Oct 2026

WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency

Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artifacts and higher-level visual inconsistencies, a plausible image can still contradict real-world facts or rules. We introduce WorldFact-Bench to evaluate image-world con...

Zhuo Chen, Zheng-Xian Wu, Yu Yu et al. · 0 citations
Preprint Aug 2026

Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos

Consistent gains over DVD on LVBench, Video-MME, EgoSchema, and LongVideoBench suggest that option-aware evidence acquisition transfers beyond MMR-V, and proposes PACE (Progressive Acquisition of Critical Evidence), a factor-guided framework for long-video evidence acquisition.

Bai-Xuan Xu, Yinyui Xu, Tianshi ZHENG et al. · 2 citations
#artificial intelligence Preprint Sep 2026

What Should We Ask Next? Retrieval-Aware Question Learning for Interactive ReID

This work establishes that candidate discriminativeness and perceived usefulness provide weak supervision for this objective, then introduces RAVEL, a retrieval-aware online reinforcement learning framework for interactive person re-identification and shows that RAVEL delivers progressively stronger retrieval performan...

Lyucheng Qian, John Yuehan Zhang, Ping-Yu Wang · 0 citations
#artificial intelligence Preprint Sep 2026

Seeing Parts, Reasoning about Worlds: Visual Inference under Partial Observation

This work introduces WorldScope, which composes cross-view entity evidence and support-surface coverage into an image-subset evidence lattice, and proposes WorldFlow, which composes cross-view entity evidence and support-surface coverage into an image-subset evidence lattice.

Wei Wang, Wen-Qiao Zhang, Yu-Tong Lin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.