Your Group-Relative Advantage Is Biased

arXiv:2601.08521 · cs.LG · Submitted 2026-01-13 · Read on arXiv

cs.LG

Submitted: 2026-01-13

Updated: 2026-10-30

Terminology

• GRPO — 2× in this paper · explained in 6 episodes
• RLVR — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Related papers

• Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
• Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
• D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
• Optimal hypersurface decision trees
• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation