The Invisible Leash: Why RLVR May or May Not Escape Its Origin

Understand

Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising method for enhancing LLMs' capabilities.

• However, it remains unclear whether the current practice of RLVR truly expands a model's reasoning boundary or mainly amplifies high-reward outputs that the base model already knows, thereby improving precision.
• This study presents an empirical investigation that provides fresh insights into the limits of RLVR.
• We examine how RLVR can operate as a support-constrained optimization mechanism that may restrict the discovery of entirely original solutions, remaining constrained by the base model's initial distribution.