Decoupling Exploration from Optimization in RLVR
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas absent from its prior training data. In practice, however, augmenting RLVR with strong novelty incentives has seen limited success and can degrade model quality.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.