Dataset Mismatch Matters in Group Relative Policy Optimization for Reinforcement Learning from Verifiable Rewards

arXiv:2611.00586 · cs.LG · Submitted 2026-10-31 · Read on arXiv

cs.LG

Submitted: 2026-10-31

Updated: 2026-10-31

Code: https://github.com/huggingface/Math-Verify

Terminology

Sources

Related papers