用摄像头+症状描述实现兽医疾病早筛，能自动处理异常并报警。
VetClaw: An Edge-Cloud Multimodal Agentic System for Veterinary Disease Screening
- 边缘设备采集图像与症状，云端多模态模型零样本分类
- 结合症状信息后准确率显著提升，优于纯图像输入
- 支持故障处理、安全规则和不确定情况升级，适合基层兽医使用
我们提出VetClaw，一个用于早期兽医疾病筛查的边缘-云多模态智能体系统。系统以摄像头为边缘感知设备，将拍摄图像及可选的症状描述发送至服务器端的视觉语言模型，实现零样本疾病分类。该系统将智能体交互与流程编排分离：OpenClaw在边缘设备上提供调度、工具调用、用户交互与通知服务；LangGraph则管理有状态的筛查流程，包括输入校验、图像传输、模型调用、安全检查、条件路由、异常处理与结构化日志记录。此设计突破静态图像分类局限，实现视觉证据收集、外部模型调用、确定性安全规则应用及诊断支持告警生成。实验表明，仅依赖图像的VLM预测性能有限，而融合症状的多模态输入显著提升零样本分类效果。因此，VetClaw将静态预测模型转变为协调、安全感知的系统，具备工具调用、流程管理、异常处理与不确定案例升级能力。
原文摘要 · Abstract (English)
We present VetClaw, an edge-cloud multimodal agentic system for early veterinary disease screening. VetClaw uses a camera module as an edge sensing device and sends captured images, together with optional symptom descriptions, to a server-hosted vision-language model for zero-shot disease classification. The system separates agent interaction from workflow orchestration: OpenClaw provides scheduling, tool access, user interaction, and notification services on the edge device, while LangGraph manages the stateful screening workflow, including input validation, image transmission, model invocation, safety checks, conditional routing, failure handling, and structured logging. This design moves beyond static image classification by enabling the system to collect visual evidence, invoke external models, apply deterministic safety rules, and generate diagnostic-support alerts. Results show that image-only VLM prediction remains limited, whereas symptom-guided and multimodal inputs improve zero-shot classification performance. Thus, VetClaw transforms a static prediction model into a coordinated, safety-aware system that can use tools, manage workflows, handle failures, and escalate uncertain cases.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。