AI RESEARCH
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
arXiv CS.CL
•
ArXi:2605.22620v1 Announce Type: cross Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or gold-standard solutions. Reinforcement learning from internal feedback (RLIF) has recently emerged as a scalable unsupervised alternative, using signals extracted from the model itself. However, existing RLIF methods typically rely on a single internal reward, which can lead to reward hacking, entropy collapse, and degraded reasoning structure.