AI RESEARCH
Binary Rewards and Reinforcement Learning: Fundamental Challenges
arXiv CS.LG
•
ArXi:2605.02375v1 Announce Type: new Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for improving reasoning in language models, yet models trained with RLVR often suffer from diversity collapse: while single-sample accuracy improves, multi-sample coverage degrades, sometimes falling below the base model. We provide a structural account of this phenomenon grounded in the properties of binary rewards.