Agent skill · research science · wshobson
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.
Why this skill is useful
Provides a detailed executable recipe for training GRPO with reinforcement learning, including specific configurations and reward functions that enhance model performance.
What it needs
Requires trl installed locally. About 4k tokens when loaded. Last updated 2026-08-05. 38,570 stars on the source repository.
What this skill does
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, schema checker, or grader) for the target task. Output format: a validated GRPO config — the kwarg values in references/grpo-memory.md and the reward functions in references/reward-functions.md, not free-form advice — that llm-finetuning-training-engineer consumes directly. When RL Applies GRPO+RLVR only pays off when task success is algorithmically checkable — a unit test passes, a parser accepts the output, a tool call matches an expected schema, a math answer matches a ground truth. If grading the output requires human judgment or a subjective rubric, that's an eval-harness and judge-calibration problem first — see eval-harness-first — not a reason to skip straight to RL. Before opening a GRPO run, confirm the model can sometimes succeed on the target task already. RL sharpens an existing capability by reweighting toward the samples that already work; it does not install a capability from zero. The model never succeeds, even at low temperature across many samples: the gap is format or task understanding, not policy refinement. Route back to SFT first (lora-qlora-recipes) and only return to this skill once the base success rate is nonzero. The model succeeds sometimes, inconsistently: this is the GRPO sweet spot — proceed to The Recipe below. The standing rule for the whole plugin: DPO for taste, GRPO for reasoning. If the signal is a preference between two acceptable outputs, that's preference-optimization, not this skill. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills wshobson/grpo-rlvr-training