Tag: NVIDIA NIM

NVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science

Posted on by faz_business



Life sciences has entered an era of computational scale, and for more than a decade, NVIDIA has built the full GPU-accelerated computing stack — spanning hardware, frameworks, libraries, models, microservices and domain-specific tools — to help researchers run more sophisticated workflows and iterate faster.

This week, Anthropic announced Claude Science, an AI workbench for science research that lets scientists converse with agents in natural language to run their work end to end.

Claude Science integrates with NVIDIA BioNeMo Agent Toolkit as a resource that scientists can access within their workflow. The toolkit packages NVIDIA-accelerated capabilities as callable skills, enabling Claude Science to select the appropriate tool, prepare valid inputs and execute the workflow — all while connecting to NVIDIA compute resources deployed anywhere. This brings NVIDIA’s accelerated models, libraries and NVIDIA NIM microservices directly into the same environment where the rest of the research happens.

The world’s largest pharmaceutical companies use NVIDIA technologies to advance AI-enabled research across drug discovery, genomics, medical imaging, molecular design and protein engineering. Today, 18 of the top 20 pharmaceutical companies use NVIDIA BioNeMo, underscoring the breadth of its role across the ecosystem.

Advancing the Agentic Era of Scientific Discovery

Claude Science lets scientists use natural language to move their research from intent into action, without manually configuring models, endpoints, or software environments. NVIDIA BioNeMo Agent Toolkit extends that with access to accelerated workflows and models like Evo 2, Boltz-2 and OpenFold3, so the analyses that benefit from acceleration run faster. 

A scientist begins by describing a research task, such as analyzing a genomic sequence, predicting a protein structure or designing a potential binder, in natural language. Claude Science interprets the request and orchestrates the work through preconfigured domain-specialized agents that know established workflows across genomics, proteomics, single-cell analysis, cheminformatics and clinical research. 

BioNeMo Agent Toolkit gives these agents the context needed to connect each step with an appropriate NVIDIA scientific capability. Each skill includes information about its purpose and required inputs, helping agents prepare and execute the workflow and return outputs for review.

The result is an iterative loop between scientific reasoning and accelerated computational work. Scientists can inspect outputs, refine their questions and determine the next step while staying focused on the science.

One powerful example is generating better inhibitors of common cancer targets. In this workflow, a scientist starts with a known cancer-causing antigen mutation and asks Claude to design numerous potential inhibitors. Claude Science integrated with BioNeMo Agent Toolkit and NVIDIA NIM microservices accelerates high-throughput inhibitor prediction, optimization and validation.

A Scientific Foundation Built for Agents

AI agents reason, plan and use tools to complete tasks. In life sciences, those tools are often specialized computational workflows. 

An autonomous AI scientist agent doesn’t reason in isolation. It may need to fingerprint a library of compounds, cluster promising hits, generate conformers for top candidates, analyze genomic context and compare perturbation responses before recommending the next experiment. 

Each step relies on a scientific tool, and the agent can only work as fast as those tools run.

NVIDIA BioNeMo Agent Toolkit gives scientific agents the accelerated tools they need to operate at the speed of science. It includes:

  • NVIDIA Parabricks accelerates genomic analysis from hours to minutes, so an agent can integrate genomic context into a decision in near real time.
  • RAPIDS-singlecell, developed by scverse, compresses a 1.3-million-cell preprocessing and clustering workflow from 52 minutes to 25 seconds, so single cell analysis becomes part of the reasoning loop rather than an offline batch of jobs.
  • nvMolKit accelerates cheminformatics operations like similarity search and conformer generation by up to 3,000x, so an agent iterating across a massive chemical space gets results at the speed of thought.
  • NVIDIA BioNeMo open models deliver core biomolecular capabilities accelerated by NVIDIA libraries, so an agent has a purpose-built scientific model for each step of a workflow.
  • BioNeMo NIM microservices package those models as enterprise-ready inference endpoints — containerized microservices with the full accelerated software stack pre-integrated and tuned for high-performance inference — so an agent can call a single stable application programming interface for production deployment.

NVIDIA BioNeMo Agent Toolkit is open and harness-agnostic, allowing the same scientific skills to work across agent frameworks and research platforms. The toolkit and its skills are available now through NVIDIA developer resources and GitHub.

Scientists can access BioNeMo-powered workflows through Anthropic’s Claude Science, which is entering public beta today. As part of the public beta, Anthropic is inviting researchers to provide feedback on additional domain specialists and integrations they need.

New NVIDIA Nemotron 3 Super Delivers 5x Higher Throughput for Agentic AI

Posted on by faz_business



Launched today, NVIDIA Nemotron 3 Super is a 120‑billion‑parameter open model with 12 billion active parameters designed to run complex agentic AI systems at scale. 

Available now, the model combines advanced reasoning capabilities to efficiently complete tasks with high accuracy for autonomous agents.

AI-Native Companies: Perplexity offers its users access to Nemotron 3 Super for search and as one of 20 orchestrated models in Computer. Companies offering software development agents like CodeRabbit, Factory and Greptile are integrating the model into their AI agents along with proprietary models to achieve higher accuracy at lower cost. And life sciences and frontier AI organizations like Edison Scientific and Lila Sciences will power their agents for deep literature search, data science and molecular understanding.

Enterprise Software Platforms: Industry leaders such as Amdocs, Palantir, Cadence, Dassault Systèmes and Siemens are deploying and customizing the model to automate workflows in telecom, cybersecurity, semiconductor design and manufacturing. 

As companies move beyond chatbots and into multi‑agent applications, they encounter two constraints.

The first is context explosion. Multi‑agent workflows generate up to 15x more tokens than standard chat because each interaction requires resending full histories, including tool outputs and intermediate reasoning. 

Over long tasks, this volume of context increases costs and can lead to goal drift, where agents lose alignment with the original objective.

The second is the thinking tax. Complex agents must reason at every step, but using large models for every subtask makes multi-agent applications too expensive and sluggish for practical applications.

Nemotron 3 Super has a 1‑million‑token context window, allowing agents to retain full workflow state in memory and preventing goal drift.

Nemotron 3 Super has set new standards, claiming the top spot on Artificial Analysis for efficiency and openness with leading accuracy among models of the same size. 

The model also powers the NVIDIA AI-Q research agent to the No. 1 position on DeepResearch Bench and DeepResearch Bench II leaderboards, benchmarks that measure an AI system’s ability to conduct thorough, multistep research across large document sets while maintaining reasoning coherence. 

Hybrid Architecture

Nemotron 3 Super uses a hybrid mixture‑of‑experts (MoE) architecture that combines three major innovations to deliver up to 5x higher throughput and up to 2x higher accuracy than the previous Nemotron Super model. 

  • Hybrid Architecture: Mamba layers deliver 4x higher memory and compute efficiency, while transformer layers drive advanced reasoning.
  • MoE: Only 12 billion of its 120 billion parameters are active at inference. 
  • Latent MoE: A new technique that improves accuracy by activating four expert specialists for the cost of one to generate the next token at inference.
  • Multi-Token Prediction: Predicts multiple future words simultaneously, resulting in 3x faster inference.

On the NVIDIA Blackwell platform, the model runs in NVFP4 precision. That cuts memory requirements and pushes inference up to 4x faster than FP8 on NVIDIA Hopper, with no loss in accuracy. 

Open Weights, Data and Recipes

NVIDIA is releasing Nemotron 3 Super with open weights under a permissive license. Developers can deploy and customize it on workstations, in data centers or in the cloud.

The model was trained on synthetic data generated using frontier reasoning models. NVIDIA is publishing the complete methodology, including over 10 trillion tokens of pre- and post-training datasets, 15 training environments for reinforcement learning and evaluation recipes. Researchers can further use the NVIDIA NeMo platform to fine-tune the model or build their own. 

Use in Agentic Systems

Nemotron 3 Super is designed to handle complex subtasks inside a multi-agent system. 

A software development agent can load an entire codebase into context at once, enabling end-to-end code generation and debugging without document segmentation. 

In financial analysis it can load thousands of pages of reports into memory,  eliminating the need to re-reason across long conversations, which improves efficiency. 

Nemotron 3 Super has high-accuracy tool calling that ensures autonomous agents reliably navigate massive function libraries to prevent execution errors in high-stakes environments, like autonomous security orchestration in cybersecurity.

Availability

NVIDIA Nemotron 3 Super, part of the Nemotron 3 family, can be accessed at build.nvidia.com, Perplexity, OpenRouter and Hugging Face. Dell Technologies is bringing the model to the Dell Enterprise Hub on Hugging Face, optimized for on-premise deployment on the Dell AI Factory, advancing multi-agent AI workflows. HPE is also bringing NVIDIA Nemotron to its agents hub to help ensure scalable enterprise adoption of agentic AI. 

Enterprises and developers can deploy the model through several partners:

The model is packaged as an NVIDIA NIM microservice, allowing deployment from on-premises systems to the cloud.

Stay up to date on agentic AI, NVIDIA Nemotron and more by subscribing to NVIDIA AI news, joining the community, and following NVIDIA AI on LinkedIn, Instagram, X and Facebook.

Explore self-paced video tutorials and livestreams.