LAMMI-Pathology: 一种以工具为中心的自下而上LVLM-智能体框架用于分子信息引导的病理学智能
LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology
AI总结：
LAMMI-Pathology提出了一种以工具为中心的自下而上智能体框架，通过分子信息引导的病理学智能提升病理图像分析的证据驱动能力。
摘要：
工具调用基于智能体系统的发展引入了一种更加证据驱动的病理图像分析范式，与粗粒度的文本-图像诊断方法形成对比。随着空间转录组学技术的大规模实验应用，分子验证的病理诊断正变得越来越开放和可访问。在本文中，我们提出了LAMMI-Pathology（分子信息引导的病理学医学智能LVLM-智能体系统），一种适用于特定领域的可扩展智能体框架。LAMMI-Pathology采用以工具为中心的自下而上架构，在其中定制的领域自适应工具作为基础。这些工具按领域风格进行聚类，形成组件智能体，然后通过顶层规划器进行协调，避免因过长的上下文长度导致的任务漂移。基于此，我们引入了一种基于原子执行节点（AENs）的新轨迹构建机制，这些节点作为可靠且可组合的单元，用于构建半模拟推理轨迹，捕捉可信的智能体-工具交互。在此基础上，我们开发了一种轨迹感知的微调策略，使规划器的决策过程与这些多步骤推理轨迹对齐，从而增强病理理解的推理鲁棒性及其对定制工具集的适应性使用。
英文摘要：
The emergence of tool-calling-based agent systems introduces a more evidence-driven paradigm for pathology image analysis in contrast to the coarse-grained text-image diagnostic approaches. With the recent large-scale experimental adoption of spatial transcriptomics technologies, molecularly validated pathological diagnosis is becoming increasingly open and accessible. In this work, we propose LAMMI-Pathology (LVLM-Agent System for Molecularly Informed Medical Intelligence in Pathology), a scalable agent framework for domain-specific agent tool-calling. LAMMI-Pathology adopts a tool-centric, bottom-up architecture in which customized domain-adaptive tools serve as the foundation. These tools are clustered by domain style to form component agents, which are then coordinated through a top-level planner hierarchically, avoiding excessively long context lengths that could induce task drift. Based on that, we introduce a novel trajectory construction mechanism based on Atomic Execution Nodes (AENs), which serve as reliable and composable units for building semi-simulated reasoning trajectories that capture credible agent-tool interactions. Building on this foundation, we develop a trajectory-aware fine-tuning strategy that aligns the planner's decision-making process with these multi-step reasoning trajectories, thereby enhancing inference robustness in pathology understanding and its adaptive use of the customized toolset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
