NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning

<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-768x432.webp" class="webfeedsFeaturedVisual wp-post-image" alt="Illustration of a central AI model connecting code, charts, credit memo data extraction, and video analysis." style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-768x432.webp 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-179x101.webp 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-300x169.webp 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-625x352.webp 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-1536x865.webp 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-2048x1153.webp 2048w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-645x363.webp 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-660x370.webp 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-500x282.webp 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-160x90.webp 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-362x204.webp 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-195x110.webp 195w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-1024x577.webp 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-960x540.webp 960w" sizes="(max-width: 768px) 100vw, 768px" title="Nemotron-3-5-Super-VL" />Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources,...<img width="768" height="432" src="https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-768x432.webp" class="webfeedsFeaturedVisual wp-post-image" alt="Illustration of a central AI model connecting code, charts, credit memo data extraction, and video analysis." style="display: block; margin-bottom: 5px; clear:both;max-width: 100%;" link_thumbnail="" decoding="async" loading="lazy" srcset="https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-768x432.webp 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-179x101.webp 179w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-300x169.webp 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-625x352.webp 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-1536x865.webp 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-2048x1153.webp 2048w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-645x363.webp 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-660x370.webp 660w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-500x282.webp 500w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-160x90.webp 160w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-362x204.webp 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-195x110.webp 195w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-1024x577.webp 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2026/10/Nemotron-3-5-Super-VL-e1792075881894-960x540.webp 960w" sizes="auto, (max-width: 768px) 100vw, 768px" title="Nemotron-3-5-Super-VL" /><p>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…</p> <p><a href="https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/" rel="nofollow" data-wpel-link="internal" target="_self">Source</a></p>