14 citations · 15 across the 4 of their papers we have counts for
4 papers · 1 filter
Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL
Zhicheng Cai, Weinan Dai, Yuyan Zhou +3
Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. Yet long-horizon autoregressive rollouts introduce a fundamental limitation:…
Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence
Zhicheng Cai, Xinyuan Guo, Hanlin Wu +5
Reinforcement learning has become the foundational paradigm for enhancing the reasoning capabilities of LLMs. Yet the dominant approach, Proximal Policy Optimization (PPO), relies…
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Weinan Dai, Hanlin Wu, Qiying Yu +13
GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general progra…
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Qiying Yu, Zheng Zhang, Ruofei Zhu +32
Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details…