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 BlogWith 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 Blog… We can improve each model with feature engineering and/or model tuning/improvements. Feature engineering focuses on transforming the data so our models can extract more signal. And model tuning/improvements focus on modifying the model to extract more signal. …
… 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. …
… Discuss 0 Discuss 0 Tags Agentic AI / Generative AI | General | Blueprint | NeMo | NIM | Beginner Technical | News | Agent toolkit | AI Agent | AI Data Platform | AI-Ready Data | featured | GTC Paris 2025 | LLMs | Retrieval Augmented Generation RAG About the Authors About Nicola Sessions Nicola Ses… …
… Ising Calibration agentic workflow and cookbook GitHub under Apache 2.0. …
Agentic AI / Generative AI Build Personal AI Agents on Windows PCs with New Tools from Microsoft and NVIDIA Turnkey agent sandboxing on native Windows is now available, plus 2x faster agentic inference, new agent apps, and more Jun 02, 2026 By Annamalai Chockalingam and Gerardo Delgado Discuss 0 Di… …
Agentic AI / Generative AI MiniMax M2.7 Advances Scalable Agentic Workflows on NVIDIA Platforms for Complex AI Applications Apr 11, 2026 By Anu Srivastava and Shruti Koparkar Discuss 0 Discuss 0 L T F R E The release of MiniMax M2.7 adds enhancements to the popular MiniMax M2.5 model, built for age… …
… Learn more Agentic code assistants are moving into daily game development as studios build larger worlds, ship more DLCs, and support distributed teams. …
… It reflects the architectural efficiency of Nemotron 3 Nano Omni when deployed in real agentic workloads. …
… That makes it useful, but only as one layer in an agentic AI control stack. …
… Learn more about the accuracy improvements with VLM for the Ragbattle dataset. …
