Individual skill
grpo-rlvr-training
Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.
plugins/llm-finetuning/skills/grpo-rlvr-training/SKILL.md
Source commit 4bde3168b43c0655c4d00ea2726e631719908a6d
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 42,274
- Repository last updated
- Nov 5, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- anthropic Repository topic
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- cursor Repository topic
- cursor-rules Repository topic
- mcp Repository topic
- multi-agent Repository topic
- opencode Repository topic
- claude-code Repository topic
- education Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,823 bytesSKILL.mdcore · 7,823 bytesreferences/grpo-memory.mddoc · 3,622 bytesreferences/reward-functions.mddoc · 11,806 bytes
Read excerpt
# GRPO & RLVR Training
This skill assumes `finetuning-method-selection`
already routed here because the target behavior
has a verifiable pass/fail signal — not
demonstrations (`lora-qlora-recipes`) or
preference pairs (`preference-optimization`).
What follows is when RL is the right tool, the
reference recipe, the mandatory reward-inspection
gate, and how to pick a GRPO variant when the
base recipe misbehaves.
**Input:** a routing decision (RLVR via GRPO)
plus a verifier (code executor, test suite,