Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2025 3representative citing papers
Prolonged RL training with KL control and reference policy resetting enables LLMs to develop novel reasoning strategies inaccessible to base models even under extensive sampling.
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.
citing papers explorer
-
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
Prefix-RFT blends SFT and RFT via prefix sampling from demonstrations to outperform standalone SFT, RFT, and mixed-policy baselines on math reasoning problems.
-
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Prolonged RL training with KL control and reference policy resetting enables LLMs to develop novel reasoning strategies inaccessible to base models even under extensive sampling.
-
Learning to Reason under Off-Policy Guidance
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.