NVIDIA NeMo Agent Toolkit
…Tech Blog Improving AI Code Generation NVIDIA NeMo Agent Toolkit, USD, Cosmos Learn how to leverage AI code generation with the toolkit to build a test-driven coding agent. Documentation NeMo Agent…
Search
People also ask
Why are SLMs beneficial to agentic AI tasks?
SLMs are well-positioned for the agentic era because they use a narrow slice of LLM functionality for any single language model errand. LLMs are built to be powerful generalists, but most agents use only a very narrow subset of their capabilities. They typically parse commands, generate structured outputs such as JSON for tool calls, or produce summaries and answer contextualized questions. These tasks are repetitive (up to the differences in prompt payloads), predictable, and highly specialized—well within the scope of specialized SLMs. An LLM trained to handle open-domain conversations is o
How Small Language Models Are Key to Scalable Agentic AI | NVIDIA Technical BlogHow are NVIDIA and the OSS community accelerating inference for local agentic AI?
With agents running 24 hours a day, seven days a week on increasingly complex tasks, efficient local compute matters even more. NVIDIA has collaborated with the open source community to enhance the top inference backends for agents, llama.cpp and vLLM. llama.cpp now delivers 2x performance on Qwen 3.5 and 3.6 27B dense models, and 1.6x performance on Qwen 3.5 and 3.6 35B mixture-of-expert (MoE) models. The following two techniques make this possible: Multi-Token Prediction (MTP): An advanced speculative decoding technique, where a smaller draft model proposes several tokens ahead that the targ
Build Personal AI Agents on Windows PCs with New Tools from Microsoft and NVIDIA | NVIDIA Technical BlogTop stories
Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning | NVIDIA Technical Blog
…An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning Mar 11, 2026 By Chris Alexiuk and Chintan Patel Discuss (0) Discuss (0) L T F R E Agentic AI systems need models…
Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints | NVIDIA Technical Blog
Agentic AI / Generative AI Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints Feb 27, 2026 By Anu Srivastava Discuss (0) Discuss (0) L T F R E…
Advance Video Analytics AI Agents Using the NVIDIA AI Blueprint for Video Search and Summarization | NVIDIA Technical Blog
…Audio transcription NVIDIA empowered blueprint-generated visual agents with the ability to hear, leading to improved contextual understanding and unlocking information not captured by video. This feature greatly improves the accuracy of…
Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform | NVIDIA Technical Blog
…Use the low-latency path where predictable token generation improves experience, such as coding assistants, agentic workflows with tight tool-calling loops, voice interactions, and real-time translation. Keep throughput-first workloads…
DeepStream SDK - Get Started
…DeepStream coding agent that enables the generation of complete video ingestion pipelines from natural language prompts Support for accelerating the development of generative AI applications, dramatically reducing development time from eight weeks…
Build Next-Gen Physical AI with Edge‑First LLMs for Autonomous Vehicles and Robotics | NVIDIA Technical Blog
…Support for an improved long-context window of up to 256K input tokens, allowing edge agents to ingest extensive environmental and historical data. By supporting Cosmos Reason 2, TensorRT Edge-LLM ensures…
Building NVIDIA Nemotron 3 Agents for Reasoning, Multimodal RAG, Voice, and Safety | NVIDIA Technical Blog
…Around them, NeMo tools add retrieval, tool‑calling, evaluation, and judge models so agents can score their own work and improve. Efficiency is the hidden requirement that makes production viable. Real agents…
Automating and Optimizing Financial Signal Discovery with Multi-Agent Systems | NVIDIA Technical Blog
…If a signal has suboptimal performance in backtesting, the evaluation agent generates optimization suggestions that are fed back into the Signal Agent’s next iteration. This creates a self-improving loop where…
NVIDIA DSX OS Delivers Open, Modular Software for Operating AI Factories at Scale | NVIDIA Technical Blog
…NVIDIA DSX’s AI factory ecosystem to adopt the latest in agentic AI infrastructure software across the full stack, improving tokens per watt and lowering token cost, accelerating deployment, and strengthening operational…