MCPO: Dynamic Masking and Multi-Comparison Policy Optimization Algorithm for LLM Reinforcement Learning
MCPO: Dynamic Masking and Multi-Comparison Policy Optimization Algorithm for LLM Reinforcement Learning
Fei Ding,Baiqiao Wang,Xiaoping-Zhang,Wenbo Ding
2026 · DOI: 10.1109/icassp55912.2026.11462267
IEEE International Conference on Acoustics, Speech, and Signal Processing · 0 Citations