Saved in:
Bibliographic Details
Main Authors: Zhang, Wenchuan, Guo, Jingru, Zhang, Hengzhe, Zhang, Penghao, Chen, Jie, Zhang, Shuwan, Zhang, Zhang, Yi, Yuhao, Bu, Hong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.02258
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914413973340160
author Zhang, Wenchuan
Guo, Jingru
Zhang, Hengzhe
Zhang, Penghao
Chen, Jie
Zhang, Shuwan
Zhang, Zhang
Yi, Yuhao
Bu, Hong
author_facet Zhang, Wenchuan
Guo, Jingru
Zhang, Hengzhe
Zhang, Penghao
Chen, Jie
Zhang, Shuwan
Zhang, Zhang
Yi, Yuhao
Bu, Hong
contents Although Vision Language Models (VLMs) have shown strong generalization in medical imaging, pathology presents unique challenges due to ultra-high resolution, complex tissue structures, and nuanced clinical semantics. These factors make pathology VLMs prone to hallucinations, i.e., generating outputs inconsistent with visual evidence, which undermines clinical trust. Existing RAG approaches in this domain largely depend on text-based knowledge bases, limiting their ability to leverage diagnostic visual cues. To address this, we propose Patho-AgenticRAG, a multimodal RAG framework with a database built on page-level embeddings from authoritative pathology textbooks. Unlike traditional text-only retrieval systems, it supports joint text-image search, enabling direct retrieval of textbook pages that contain both the queried text and relevant visual cues, thus avoiding the loss of critical image-based information. Patho-AgenticRAG also supports reasoning, task decomposition, and multi-turn search interactions, improving accuracy in complex diagnostic scenarios. Experiments show that Patho-AgenticRAG significantly outperforms existing multimodal models in complex pathology tasks like multiple-choice diagnosis and visual question answering. Our project is available at the Patho-AgenticRAG repository: https://github.com/Wenchuan-Zhang/Patho-AgenticRAG.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02258
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
Zhang, Wenchuan
Guo, Jingru
Zhang, Hengzhe
Zhang, Penghao
Chen, Jie
Zhang, Shuwan
Zhang, Zhang
Yi, Yuhao
Bu, Hong
Computer Vision and Pattern Recognition
Although Vision Language Models (VLMs) have shown strong generalization in medical imaging, pathology presents unique challenges due to ultra-high resolution, complex tissue structures, and nuanced clinical semantics. These factors make pathology VLMs prone to hallucinations, i.e., generating outputs inconsistent with visual evidence, which undermines clinical trust. Existing RAG approaches in this domain largely depend on text-based knowledge bases, limiting their ability to leverage diagnostic visual cues. To address this, we propose Patho-AgenticRAG, a multimodal RAG framework with a database built on page-level embeddings from authoritative pathology textbooks. Unlike traditional text-only retrieval systems, it supports joint text-image search, enabling direct retrieval of textbook pages that contain both the queried text and relevant visual cues, thus avoiding the loss of critical image-based information. Patho-AgenticRAG also supports reasoning, task decomposition, and multi-turn search interactions, improving accuracy in complex diagnostic scenarios. Experiments show that Patho-AgenticRAG significantly outperforms existing multimodal models in complex pathology tasks like multiple-choice diagnosis and visual question answering. Our project is available at the Patho-AgenticRAG repository: https://github.com/Wenchuan-Zhang/Patho-AgenticRAG.
title Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.02258