A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology

# A Multi-modal Agentic Co-pilot for Evidence Grounded Computational Pathology
Source: [https://arxiv.org/abs/2606.08093](https://arxiv.org/abs/2606.08093)
Authors:[Zhe Xu](https://arxiv.org/search/cs?searchtype=author&query=Xu,+Z),[Zhengyu Zhang](https://arxiv.org/search/cs?searchtype=author&query=Zhang,+Z),[Zhiyuan Cai](https://arxiv.org/search/cs?searchtype=author&query=Cai,+Z),[Jiahao Xu](https://arxiv.org/search/cs?searchtype=author&query=Xu,+J),[Yijie Lin](https://arxiv.org/search/cs?searchtype=author&query=Lin,+Y),[Ziyi Liu](https://arxiv.org/search/cs?searchtype=author&query=Liu,+Z),[Junlin Hou](https://arxiv.org/search/cs?searchtype=author&query=Hou,+J),[Hongyi Wang](https://arxiv.org/search/cs?searchtype=author&query=Wang,+H),[Yuxiang Nie](https://arxiv.org/search/cs?searchtype=author&query=Nie,+Y),[Ling Liang](https://arxiv.org/search/cs?searchtype=author&query=Liang,+L),[Yihui Wang](https://arxiv.org/search/cs?searchtype=author&query=Wang,+Y),[Yingxue Xu](https://arxiv.org/search/cs?searchtype=author&query=Xu,+Y),[Ronald Cheong Kin Chan](https://arxiv.org/search/cs?searchtype=author&query=Chan,+R+C+K),[Li Liang](https://arxiv.org/search/cs?searchtype=author&query=Liang,+L),[Hao Chen](https://arxiv.org/search/cs?searchtype=author&query=Chen,+H)

[View PDF](https://arxiv.org/pdf/2606.08093)

> Abstract:Pathology is the cornerstone of modern medicine, where accurate decision\-making relies heavily on evidence\-based practices\. While artificial intelligence \(AI\) has the potential to transform clinical workflows, the intersection of AI and evidence\-based medicine remains under\-explored, with primitive attempts restricted to text\-only general medicine\. In this work, we present PathPocket, a multimodal AI agentic co\-pilot designed specifically for evidence grounded pathology\. We construct the most comprehensive pathology evidence corpus to date, encompassing approximately 110,472 public and authorized documents structured across a rigorous hierarchy of evidence from clinical guideline to expert opinion\. From this meticulously graded foundation, we build a large\-scale multimodal pathology hypergraph containing over 4\.55 million entities and 7\.10 million relations\. Serving as a robust knowledge engine, this hypergraph provides traceable evidence for a collaborative multi\-agent reasoning framework integrating input understanding, evidence retrieval, filtering, and diagnosis generation\. This enables PathPocket to seamlessly resolve a wide spectrum of clinical tasks, ranging from text\-only queries to complex multimodal diagnostics involving region\-of\-interest \(ROI\) and gigapixel whole\-slide images \(WSIs\)\. We rigorously evaluate the system on a multidimensional benchmark of over 200,000 real\-world cases, where it significantly outperforms existing state\-of\-the\-arts\. Crucially, extensive user studies demonstrate that PathPocket substantially improves the diagnostic accuracy and confidence of pathologists\. By directly grounding pathology interpretations in verifiable literature, PathPocket offers a practical and scalable solution for the future of evidence grounded computational pathology\.

## Submission history

From: Zhe Xu \[[view email](https://arxiv.org/show-email/819d8534/2606.08093)\] **\[v1\]**Sat, 6 Jun 2026 10:36:30 UTC \(3,285 KB\)