NVIDIA 发布 Nemotron 3.5 Super VL 多模态智能体模型
原标题：NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning
AI 摘要
NVIDIA 发布 Nemotron 3.5 Super VL，一个开放可定制的多模态模型，采用 120B 参数 MoE 架构，每 token 激活 12B 参数，单 GPU 上 agentic 任务吞吐量最高提升 5 倍。该模型融合推理、指令遵循、工具使用与文本、图像、文档、视频理解，开发者可用 NVIDIA NeMo 基于自有数据进行后训练，构建企业专用智能体。Scale AI、Ramp、AI21 与 Alice 等公司已将其用于信贷处理、票据结构化、威胁情报等场景，报告了显著的成本、延迟和准确率改善。
正文节选
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 parameters per token, balancing model capacity with inference efficiency. On a single GPU, this model delivers u