nemo-rl-auto-research

Automates NeMo-RL research campaigns with TSV logging and durable ledgers.

Updated Apr 16, 2026

Search Tags:#baseline #reproducibility #git-workflow #experiment-management #autoresearch #nemo-rl #tsv-logs

Ready to run

npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill nemo-rl-auto-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nemo-rl-auto-research
Source: https://github.com/sayalinvidia/sayali-skills-test/tree/main/skills/nemo-rl-auto-research
Command: npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill nemo-rl-auto-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates end-to-end NeMo-RL research campaigns, guiding agents through the full experiment lifecycle from recipe understanding to reproducible baselines and iterative discovery.

Core Features & Use Cases

Orchestrates baseline setup, branch-based hypothesis experiments, and per-experiment logging using TSV ledgers.
Reads target recipes and relevant code paths, enforces branching discipline, and preserves a complete audit trail of campaign decisions.
Integrates safety checks, per-experiment budgets, and a memory of session state to support resume and handoff in long-running campaigns.

Quick Start

Provide a campaign plan and start a baseline auto-research run against a chosen NeMo-RL recipe.

Frequently Asked Questions about nemo-rl-auto-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate end-to-end NeMo-RL experiments with reproducible baselines?▼

Automate NeMo-RL experiments by orchestrating baseline setup, branch-based hypothesis trials, and per-experiment TSV logging. It reads target recipes, enforces branching discipline, and maintains a complete audit trail of campaign decisions for full reproducibility.

What's the best way to manage iterative reinforcement learning trials and log results?▼

Manage iterative reinforcement learning trials by creating a branch per hypothesis under a shared prefix and enforcing stop rules. Results are written to a durable TSV ledger recording metadata such as branch, commit, metric, memory, and log paths.

Does NeMo-RL auto-research support resuming long-running experiment campaigns?▼

Long-running experiment campaigns are supported through a session memory that preserves state. This enables resume and handoff capabilities, while safety checks and per-experiment budgets ensure controlled execution across extended research runs.

How do I enforce git workflow discipline when testing multiple reinforcement learning hypotheses?▼

Enforce git workflow discipline by creating a dedicated branch per hypothesis under a shared prefix for each experiment. The system checks prerequisites and records commit metadata, ensuring every iterative trial remains isolated and reproducible.

What format does the experiment ledger use to track NeMo-RL metrics and metadata?▼

The experiment ledger uses TSV format to track NeMo-RL metrics and metadata. It records per-experiment results including branch names, commit hashes, metrics, memory state, and log paths to maintain a durable audit trail across campaigns.