AIBullisharXiv – CS AI · 14h ago7/10
🧠
Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
Researchers introduce RL^V, a reinforcement learning method that unifies LLM reasoners with generative verifiers to improve test-time compute scaling. The approach achieves over 20% accuracy gains on MATH benchmarks and enables 8-32x more efficient test-time scaling compared to existing RL methods by preserving and leveraging learned value functions.