NVIDIA 发布 Nemotron 3.5 Super VL 多模态模型，面向专用智能体
NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning
NVIDIA 发布 Nemotron 3.5 Super VL，一个面向专用工作流的开放可定制多模态模型，采用 120B 参数 MoE 架构、激活 12B 参数。该模型针对持续运行的智能体场景，单次请求可能涉及读取文档、跨来源核对信息、遵循公司政策并调用多个工具。
同一新闻，精选展示《NVIDIA 扩展 Nemotron 家族，发布 Nemotron 3.5 Super VL 与 Bolt 系列模型》
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…
来源：NVIDIA Technical Blog · developer.nvidia.com