NVIDIA NeMo Gym: framework for evaluating and improving models and agents using environments
NVIDIA's NeMo team has published a Python library called NeMo Gym on GitHub, designed to evaluate and improve models and agents through environment-based interaction. The repository has 941 stars with minimal recent traction (+1 today). It appears to be an RL-style evaluation and training harness within the NeMo ecosystem.
Related guides (3)
Related events (8)
NVIDIA PhysicsNeMo: open-source Physics-ML deep learning framework
NVIDIA has published PhysicsNeMo, an open-source Python framework for building, training, and fine-tuning deep learning models using Physics-ML methods. The repository has accumulated 2,933 stars on GitHub. Physics-informed ML is a growing area relevant to scientific computing and simulation workloads.
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
NVIDIA and Hugging Face present an evaluation methodology for the Nemotron 3 Nano model using the NeMo Evaluator framework. The post describes benchmark results and an open evaluation recipe intended to standardize how small/nano-scale models are assessed. It positions NeMo Evaluator as a reproducible, open evaluation stack for the community.
Measuring Open-Source Llama Nemotron Models on DeepResearch Bench
NVIDIA evaluates its open-source Llama Nemotron models on the DeepResearch Bench, a benchmark designed to assess deep research agent capabilities. The post appears to report competitive performance of the Nemotron models in agentic research tasks. This is relevant to the ongoing development of open-weights models capable of multi-step research and reasoning workflows.
OpenAI Gym Beta Release
OpenAI released the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning algorithms. The toolkit includes a suite of environments ranging from simulated robots to Atari games, along with a site for comparing and reproducing results. This represented a significant early infrastructure contribution to the RL research community.
Nvidia Nemotron 3 Ultra: hybrid Mamba-transformer open-weights model targeting agentic workloads
Nvidia released Nemotron 3 Ultra, a 550B parameter (55B active) hybrid Mamba-transformer mixture-of-experts model with a 1M token context window, publishing weights, training data, and RL environments under an open license. The model ranks as the highest-scoring U.S. open-weights model on the Artificial Analysis Intelligence Index (47.7-48.2) and is approximately three times faster than comparable open-weights rivals, though it trails leading Chinese models like Kimi K2.6 and DeepSeek V4 Pro on intelligence benchmarks. Nvidia used a novel Multi-Teacher On-Policy Distillation approach with 10+ specialized teacher models and trained using NVFP4 quantization. The release is strategically motivated by Nvidia's interest in a healthy open-weights ecosystem that drives AI semiconductor adoption.
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
NVIDIA has released Nemotron 3 Nano Omni, a multimodal model targeting long-context understanding across documents, audio, and video modalities. The model is positioned for agentic use cases requiring cross-modal reasoning. It is published via the Hugging Face blog as part of NVIDIA's Nemotron model family. No detailed technical specifications or benchmark results are provided in the available body text.
OpenAI Releases Neural MMO: Massively Multiagent RL Game Environment
OpenAI released Neural MMO, a massively multiagent game environment designed for reinforcement learning research. The platform supports a large and variable number of agents operating within a persistent, open-ended task structure. The environment is designed to encourage emergent behaviors including better exploration, divergent niche formation, and improved overall agent competence through multi-species competition.
NVIDIA NeMo Megatron-Bridge: Bidirectional Hugging Face Conversion for Megatron-Based Training
Megatron-Bridge is an NVIDIA NeMo training library for Megatron-based models that supports bidirectional conversion between Megatron and Hugging Face formats. The repository has accumulated 670 stars with modest daily growth (+5). It addresses a practical interoperability gap between the high-performance Megatron training stack and the broader HuggingFace ecosystem.