EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology

[2607.19261] EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2607.19261 (cs) [Submitted on 21 Jul 2026 ( v1 ), last revised 25 Aug 2026 (this version, v4)] Title: EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology Authors: Dankai Liao , Tianyi Zhang , Yufeng Wu , Xinyue Zhang , Qiaochu Xue , Zeyu Liu , Dachun Zhao , Linghan Cai , Yueming Jin View PDF HTML (experimental) Abstract: Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scale evidence. However, most pathology benchmarks evaluate models on pre-cropped patches or pre-extracted slide features, leaving their ability to acquire evidence from gigapixel WSIs largely untested. We introduce EviPathBench, a benchmark for evaluating evidence acquisition and reasoning in vision-language models (VLMs) for whole-slide pathology. It evaluates four capabilities: image-to-text matching for evidence interpretation, text-to-image retrieval for evidence verification, diagnostic-region localization for evidence acquisition, and multi-scale reasoning for evidence integration. The benchmark is organized as a diagnostic tree linking nested regions across magnifications with scale-specific findings and path-level diagnoses. It contains 1,822 TCGA WSIs and 17,135 diagnostic paths annotated by ten board-certified pathologists. A private cohort of 190 breast cancer WSIs with detailed annotations further evaluates autonomous whole-slide exploration. We evaluate 19 VLMs spanning general-purpose, medical, and pathology-specialized families, plus one text-only reference model. Leading open-weight models achieve over 93% accuracy in multi-scale reasoning and over 50% in both cross-modal matching tasks. In contrast, diagnostic-region localization remains challenging: the best text-guided mean intersection-over-union is below 0.09, underperforming a center-based heuristic. During autonomous exploration, the unconditional hit rate drops from 0.522 at low magnification to 0.185 at intermediate magnification and 0.020 at high magnification. These results reveal a pronounced gap between reasoning over curated evidence and acquiring it from WSIs. EviPathBench provides a unified framework for measuring and improving both capabilities. Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2607.19261 [cs.CV] (or arXiv:2607.19261v4 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2607.19261 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Dankai Liao [ view email ] [v1] Tue, 21 Jul 2026 16:33:44 UTC (12,777 KB) [v2] Thu, 30 Jul 2026 09:25:28 UTC (15,160 KB) [v3] Sat, 22 Aug 2026 04:28:42 UTC (13,241 KB) [v4] Tue, 25 Aug 2026 05:53:43 UTC (14,454 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2026-07 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology#670694
• PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image#386909
• LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions#1050357
• PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?#414159
• Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence#986957