2 papers
cs.AI2026
Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation
Zhongyi Li, Wan Tian, Xiang Xu +4
Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards…
cs.AI2026
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
Wan Tian, Zhongyi Li, Xiang Xu +3
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the under…