清华、快手提出AttnRL：让大模型用「注意力」探索
"过程监督" 相关文章
COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes
Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning
Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
🚫万能Agent兜底：当规划缺失工具时，AI如何自救
SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
奥特曼：ChatGPT只是意外，全能AI智能体才是真爱！Karpathy：7年前就想到了
RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
北大团队提出LongRePS框架：面向长上下文场景的思维链过程监督方案
Outcome-Refining Process Supervision: Advancing Code Generation with Structured Reasoning and Execution Feedback
Researchers from SynthLabs and Stanford Propose Meta Chain-of-Thought (Meta-CoT): An AI Framework for Improving LLM Reasoning
Google DeepMind Researchers Propose a Novel Divide-and-Conquer Style Monte Carlo Tree Search (MCTS) Algorithm ‘OmegaPRM’ for Efficiently Collecting High-Quality Process Supervision Data
