6 papers
When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
Jiakang Wang, Runze Liu, Qingpeng Cai +7
Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimiz…
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv +7
Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribu…
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv +5
Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in m…
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Zhenpeng Su, Leiyu Pan, Xue Bai +8
We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple…
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi +11
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more…
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models
Haoran Lian, Junmin Chen, Wei Huang +8
Recently, Large language models (LLMs) have revolutionized Natural Language Processing (NLP). Pretrained LLMs, due to limited training context size, struggle with handling long tok…