Rlvr Update Direction Analysis

Analyze reinforcement learning with verifiable rewards using signed log-probability differences to identify reasoning-critical tokens. Reveals that RLVR updates concentrate on low-probability tokens, enabling test-time amplification and training-time reweighting techniques.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit ef70225724

Frequently asked questions

npx get-skill add adu2021/rlvr-update-direction-analysis