AI RESEARCH
GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
arXiv CS.AI
•
ArXi:2606.04516v1 Announce Type: cross Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation costs, while unsupervised alternatives suffer from severe model collapse. Recent semi-supervised RLVR methods address this by using a small labeled set to guide unlabeled data, achieving a promising trade-off between