AI 中文总结
CyberNeuro是配备WandaMind本地LLM的隐私保护智能体工作台，通过四个专用智能体实现神经影像与临床数据分析自动化，在NeuroBench上提升了域准确率，还降低了令牌使用量。
AI 中文摘要
尽管神经影像方法学已取得巨大成功，但将大规模高维数据集准备好用于AI/ML应用仍是关键操作瓶颈。传统工作流需要在元数据整理、流水线执行、后处理质量控制及数据管理方面投入大量人工，这种负担会不成比例地将人力和计算基础设施有限的实验室排除在外。为解决这一现实障碍，亟需可扩展、高性价比的计算平台，以普及先进神经影像分析并加速心理健康及临床转化领域的发现。依托多智能体大语言模型（LLM）的突破，我们推出CyberNeuro，这是一款配备定制本地LLM模型（WandaMind）的智能体工作台，用于自动化神经影像与健康数据分析。CyberNeuro由四个专用智能体（规划器Planner、验证器Validator、调度器Dispatcher及报告器Reporter）驱动，通过安全MCP桥接和固定执行层通信，使研究人员能使用自然语言执行复杂工作流，同时保持临床级数据隐私。在公开NeuroBench套件上，CyberNeuro将保留域准确率从基线模型的40%提升至69%。除自动化指标外，该平台还集成了人在回路验证面板，以确保严格的生物医学质量控制。在相同的端到端10批次队列工作流套件中，与Neuroclaw相比，本地WandaMind配置完成所有任务的估计总令牌数中，WandaMind约占10.6%，云提供商约占61.7%。该平台及其可投入生产的模块可在指定URL获取。
英文摘要
Despite tremendous success in neuroimaging methodology, making large-scale, high-dimensional datasets ready for AI/ML applications remains a critical operational bottleneck. Conventional workflows require extensive manual effort across metadata curation, pipeline execution, post-processing quality control, and data management, a burden that disproportionately excludes laboratories with limited manpower and computational infrastructure. To address this real-world barrier, there is an urgent need for scalable, cost-effective computational platforms that democratize advanced neuroimaging analytics and accelerate discoveries in mental health and clinical translation. Capitalizing on multi-agent LLM breakthroughs, we introduce CyberNeuro, an agentic workbench with a tailored local LLM-model ('WandaMind') for automated neuroimaging and health-data analysis. Driven by four dedicated agents (Planner, Validator, Dispatcher, and Reporter) communicating via a secure MCP bridge and a pinned execution layer, CyberNeuro enables researchers to execute complex workflows using natural language while maintaining clinical-grade data privacy. On the public NeuroBench suite, CyberNeuro increases held-out domain accuracy from 40% to 69% over the baseline model. Beyond automated metrics, the platform integrates a human-in-the-loop verification panel to ensure rigorous biomedical quality control. Across the same end-to-end 10-batch cohort workflow suite, the local WandaMind configuration completed all tasks with an estimated aggregate token count of about 10.6% using WandaMind and 61.7% using cloud providers of token usage, compared to Neuroclaw, respectively. The platform and its production-ready modules are available at https://wanda-cyberbench.com.
Comments25 pages, 4 figures
