Nemo Rl Auto Research

by nvidiacf5224d14250Apache-2.03.5K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.

Only the file list is public. File contents are available once the skill is installed in a workspace.

PathSizeType
BENCHMARK.md4.2 KBtext/markdown
evals/evals.json3.1 KBapplication/json
references/experiment-log-template.md2.5 KBtext/markdown
references/exploration-ideas.md5.5 KBtext/markdown
references/git-workflow.md3.8 KBtext/markdown
skill-card.md4 KBtext/markdown
SKILL.md9 KBtext/markdown
skill.oms.sig5.2 KBtext/plain

Source and attribution

Source:nvidia/skillsinskills/nemo-rl-auto-researchat commitcf5224d

License: Apache-2.0

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal