Contributors: David Austin, Raja Biswas, Gilberto Titericz Junior, NVIDIA.

It has been revealed that NVIDIA’s AI-Q Blueprint—the leading portable, open deep research agent—recently climbed to the top of the Hugging Face “LLM with Search” leaderboard on DeepResearch Bench. This is a significant step forward for the open-source AI stack, proving that developer-accessible models can power advanced agentic workflows that rival or surpass closed alternatives.

Sources indicate that what sets AI-Q apart? It fuses two high-performance open LLMs—Llama 3.3-70B Instruct and Llama-3.3-Nemotron-Super-49B-v1.5—to orchestrate long-context retrieval, agentic reasoning, and robust synthesis.

The AI-Q reference example also includes:.

The architecture supports parallel, low-latency search over local and web data, making it ideal for use cases that demand privacy, compliance, or on-premise deployment for reduced latency.

According to recent reports, NVIDIA Llama Nemotron Super isn’t just a fine-tuned instruct model—it’s post-trained for explicit agentic reasoning and supports reasoning ON/OFF toggles via system prompts. You can use it in standard chat LLM mode or switch to deep, chain-of-thought reasoning for agent pipelines—enabling dynamic, context-sensitive workflows.

In a recent development, one of the core strengths of AI-Q is transparency—not just in outputs, but in reasoning traces and intermediate steps. During development, the NVIDIA team leveraged both standard and new metrics, such as:.

The architecture lends itself perfectly to granular, stepwise evaluation and debugging—one of the biggest pain points in agentic pipeline development.

Sources indicate that deepResearch Bench evaluates agent stacks using a set of 100+ long-context, real-world research tasks (across science, finance, art, history, software, and more). Unlike traditional QA, tasks require report-length synthesis and complex multi-hop reasoning:.

It has been revealed that the open-source ecosystem is rapidly closing the gap—and, in some areas, leading—on real-world agent tasks that matter. AI-Q, built on Llama Nemotron, demonstrates that you don’t need to compromise on transparency or control to achieve state-of-the-art results.

Try the stack or adapt it to your own research agent projects from Hugging Face or build.nvidia.com.

→ Read original article