Are Verifier Errors Independent Within a GRPO Group? Evidence from Qwen2.5 Rollouts

arXiv:2609.06386 · cs.LG, cs.CL · Submitted 2026-09-06 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-09-06

Updated: 2026-09-06

Comments: 10pages, 4 figures, code and data in https://github.com/ethxin0011/rlvr_group_correlation

Code: https://github.com/ethxin0011/rlvr_group_correlation

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verifier — 5× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks