SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
Conservative Q-Learning for Offline Reinforcement Learning , url =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it