PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Pathology Image

WILSON - a pathology foundation model framework for patient-level analysis and diagnostic text generation

Pathologists integrate morphology across magnifications and across the slides of a patient case, whereas pathology foundation models encode thousands of tiles from single slides and aggregate their features. Here we present WILSON, a vision--language foundation model that represents whole-slide images and multi-slide c...

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.

Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models

Pathology vision-language models (VLMs) are conventionally evaluated by accuracy, but accuracy alone does not measure evidence use: it may conflate dataset contamination, prior knowledge, and image evidence. In a motivating study of lymph-node metastasis prediction, we found that most public pathology VLMs showed minim...

Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation

A clinically curated Pan-Asia WSI--report dataset is introduced and the REG 2025 benchmark is established as a benchmark for evaluating WSI-based structured report generation and vision-language understanding in computational pathology, providing insights for the design of clinically grounded multimodal pathology model...

Segment anything in pathology images with natural language

An Automated, Contamination-Controlled VQA Benchmark for Evaluating Vision-Language Models on 3D Oncology Imaging

Vision-language models (VLMs) are increasingly applied to medical imaging, yet public benchmarks may reward memorization over perception: their images and questions can enter pretraining corpora, and many items remain answerable from question text alone. We present an automated, agent-driven pipeline that builds multip...