作者位次 #3/6ACL 2026Findings· Findings of ACL
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
Yiming Huang · Zhenbo Shi · Shuzheng Gao · Cuiyun Gao · Peiyi Han · Chuanyi Liu
摘要
Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model’s evolving reasoning capabilities. T...