Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #28548

NeMo Gym

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

MODELS · 1 SOURCE · NVIDIA Developer

NVIDIA releases Nemotron 3.5 Super VL post-training recipe and Litmus‑Bench V2.0 for scientific LLMs

NVIDIA published a practical recipe to post-train its open multimodal model Nemotron 3.5 Super VL for scientific tasks using NeMo Gym and NeMo RL, and released the Nemotron RL Litmus‑Bench V2.0 dataset and benchmark for molecular-property evaluation. In a drug‑metabolism example using MetxBioDB records, supervised fine-tuning reportedly improved accuracy by 12% and subsequent RL post‑training improved it by a further 17% under a 16,384‑token output budget; an optional distillation step using a stronger teacher model such as Claude Sonnet 5.5 is shown as a way to warm‑start RL.

7.0

CODING · 1 SOURCE · NVIDIA Developer

NVIDIA releases NemoClaw blueprint showing how NeMo Compass and NeMo Eval Author turn agent failures into tests

NVIDIA published the NemoClaw blueprint and accompanying GitHub tutorial that show a complete optimization cycle using NeMo Compass, NeMo Eval Author, and NVIDIA NeMo Relay to analyze agent traces, create targeted evaluations, update agent harnesses (for example modifying Hermes SOUL.md), and re-run tests to verify fixes and catch regressions. The workflow includes examples (a Hermes enterprise assistant and a Dassault Systèmes engineering case) and tools/formats such as NeMo Gym, Harbor evaluations, ETHOS.md behavioral rules, and Model Context Protocol integrations.

6.0