AI RESEARCH
When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards
arXiv CS.LG
•
ArXi:2605.25864v1 Announce Type: new Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewards (RLVR). Nonetheless, RLVR intrinsically relies on ground-truth labels for reward computation, the acquisition of which is often prohibitively expensive in real-world scenarios. While unsupervised RLVR paradigms attempt to circumvent this by