CATPO introduces an informativeness score F(T) and critique-guided healing for failed trees to improve efficiency and performance in tree-based RLVR, reaching 37.5% macro accuracy on math benchmarks.
arXiv preprint arXiv:2402.10963 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Training Language Models to Self-Correct via Reinforcement Learning
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.