智能体
developer.nvidia.com ·
@Michelle Horton
NVIDIA Nemotron 3.5 Super VL:以多模态推理驱动专用 Agent
NVIDIA 开发者博客介绍 Nemotron 3.5 Super VL,一款面向企业级长流程 Agent 的开源可定制多模态模型。其采用 120B 参数 MoE 架构,推理时激活 12B 参数,目标场景包括文档阅读、跨源信息核对、遵循公司政策与多工具调用。文中未提供基准测试或部署效果数据。
AI推荐理由 NVIDIA 开发者博客发布的官方模型介绍,给出 Nemotron 3.5 Super VL 的具体架构信息:120B 参数 MoE、激活 12B,定位为面向企业长流程 Agent 的开源可定制多模态模型。新信息明确(模型规格与用途),对多模态 Agent 落地有参考价值;但正文片段仅到架构参数即截断,缺少基准测试、许可条款和实际部署证据,无法验证效果,故未给更高分。
78
正文
Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources,...
Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources, following company policy, and calling several tools. NVIDIA Nemotron 3.5 Super VL is an open, customizable multimodal model for these specialized workflows. Its 120B-parameter mixture-of-experts (MoE) architecture activates 12B…
Source