{"ID":2892864,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14680","arxiv_id":"2507.14680","title":"WSI-Agents: A Collaborative Multi-Agent System for Multi-Modal Whole Slide Image Analysis","abstract":"Whole slide images (WSIs) are vital in digital pathology, enabling gigapixel tissue analysis across various pathological tasks. While recent advancements in multi-modal large language models (MLLMs) allow multi-task WSI analysis through natural language, they often underperform compared to task-specific models. Collaborative multi-agent systems have emerged as a promising solution to balance versatility and accuracy in healthcare, yet their potential remains underexplored in pathology-specific domains. To address these issues, we propose WSI-Agents, a novel collaborative multi-agent system for multi-modal WSI analysis. WSI-Agents integrates specialized functional agents with robust task allocation and verification mechanisms to enhance both task-specific accuracy and multi-task versatility through three components: (1) a task allocation module assigning tasks to expert agents using a model zoo of patch and WSI level MLLMs, (2) a verification mechanism ensuring accuracy through internal consistency checks and external validation using pathology knowledge bases and domain-specific models, and (3) a summary module synthesizing the final summary with visual interpretation maps. Extensive experiments on multi-modal WSI benchmarks show WSI-Agents's superiority to current WSI MLLMs and medical agent frameworks across diverse tasks.","short_abstract":"Whole slide images (WSIs) are vital in digital pathology, enabling gigapixel tissue analysis across various pathological tasks. While recent advancements in multi-modal large language models (MLLMs) allow multi-task WSI analysis through natural language, they often underperform compared to task-specific models. Collabo...","url_abs":"https://arxiv.org/abs/2507.14680","url_pdf":"https://arxiv.org/pdf/2507.14680v1","authors":"[\"Xinheng Lyu\",\"Yuci Liang\",\"Wenting Chen\",\"Meidan Ding\",\"Jiaqi Yang\",\"Guolin Huang\",\"Daokun Zhang\",\"Xiangjian He\",\"Linlin Shen\"]","published":"2025-07-19T16:11:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}