Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29921-29929
DOI: 10.1609/aaai.v40i35.40239 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wenchuan Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Although Vision Language Models (VLMs) have shown generalization in medical imaging, pathology presents unique challenges due to ultra-high resolution, complex tissue structures, and nuanced 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 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.
Zitieren
APA
Zhang, W., Guo, J., Zhang, H., Zhang, P., Chen, J., Zhang, S., Zhang, Z., Yi, Y., & Bu, H. (2026). Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29921-29929. https://doi.org/10.1609/aaai.v40i35.40239
Vancouver
Zhang W, Guo J, Zhang H, Zhang P, Chen J, Zhang S, et al. Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29921-29929. doi:10.1609/aaai.v40i35.40239
BibTeX
@article{Zhang2026,
author = {Zhang, Wenchuan and Guo, Jingru and Zhang, Hengzhe and Zhang, Penghao and Chen, Jie and Zhang, Shuwan and Zhang, Zhang and Yi, Yuhao and Bu, Hong},
title = {Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {35},
pages = {29921--29929},
doi = {10.1609/aaai.v40i35.40239}
}
EUVIMED