Saved in:
Bibliographic Details
Main Authors: Yang, Chunze, Liu, Qidong, Zhao, Wenjie, Tang, Yue, Ge, Jiusong, Zhang, Di, Liu, Jiashuai, Wu, Lei, Lu, Junbo, Zhang, Ni, Wu, Xian, Gao, Zeyu, Li, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.23559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918518316859392
author Yang, Chunze
Liu, Qidong
Zhao, Wenjie
Tang, Yue
Ge, Jiusong
Zhang, Di
Liu, Jiashuai
Wu, Lei
Lu, Junbo
Zhang, Ni
Wu, Xian
Gao, Zeyu
Li, Chen
author_facet Yang, Chunze
Liu, Qidong
Zhao, Wenjie
Tang, Yue
Ge, Jiusong
Zhang, Di
Liu, Jiashuai
Wu, Lei
Lu, Junbo
Zhang, Ni
Wu, Xian
Gao, Zeyu
Li, Chen
contents Whole-slide image visual question answering (WSI-VQA) frames pathology as an extreme-context search problem: to answer a free-form clinical query, a system must first navigate a gigapixel slide under a strict inspection budget to locate sparse, high-resolution evidence. Existing approaches largely fall into two paradigms: i) supervised pathology multimodal large language models (MLLMs) and agents can absorb localization and reasoning into learned modules, but they often couple navigation to task-specific supervision and retraining, limiting their practicality; ii) training-free pathology agents avoid this cost by keeping core models frozen, but often follow a question-first design, constructing the initial candidate set mainly from query-conditioned relevance. This can miss decisive morphology that is not named in the question, and force heavier inference-time scaffolding. To address this challenge, we introduce PathNavigate, a training-free pathology agent built around a scan-search-readout routine. Before question matching, PathNavigate scans the current slide at low magnification with a shared online memory module over frozen pathology features, producing a slide-specific surprise field that marks an abnormal-region pool. It then applies question-conditioned PLIP relevance only within this pool to select high-magnification search targets. Finally, it extracts local high-magnification evidence and answers with a frozen perceptor-adjudicator stack, using the same online memory as slide-level context. Experiments on WSI-VQA and SlideBench-BCNB show that the proposed scan-search-readout design improves answer accuracy and yields more interpretable evidence-selection trajectories with higher efficiency.The code is available online.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23559
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA
Yang, Chunze
Liu, Qidong
Zhao, Wenjie
Tang, Yue
Ge, Jiusong
Zhang, Di
Liu, Jiashuai
Wu, Lei
Lu, Junbo
Zhang, Ni
Wu, Xian
Gao, Zeyu
Li, Chen
Computer Vision and Pattern Recognition
Artificial Intelligence
Whole-slide image visual question answering (WSI-VQA) frames pathology as an extreme-context search problem: to answer a free-form clinical query, a system must first navigate a gigapixel slide under a strict inspection budget to locate sparse, high-resolution evidence. Existing approaches largely fall into two paradigms: i) supervised pathology multimodal large language models (MLLMs) and agents can absorb localization and reasoning into learned modules, but they often couple navigation to task-specific supervision and retraining, limiting their practicality; ii) training-free pathology agents avoid this cost by keeping core models frozen, but often follow a question-first design, constructing the initial candidate set mainly from query-conditioned relevance. This can miss decisive morphology that is not named in the question, and force heavier inference-time scaffolding. To address this challenge, we introduce PathNavigate, a training-free pathology agent built around a scan-search-readout routine. Before question matching, PathNavigate scans the current slide at low magnification with a shared online memory module over frozen pathology features, producing a slide-specific surprise field that marks an abnormal-region pool. It then applies question-conditioned PLIP relevance only within this pool to select high-magnification search targets. Finally, it extracts local high-magnification evidence and answers with a frozen perceptor-adjudicator stack, using the same online memory as slide-level context. Experiments on WSI-VQA and SlideBench-BCNB show that the proposed scan-search-readout design improves answer accuracy and yields more interpretable evidence-selection trajectories with higher efficiency.The code is available online.
title PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.23559