作者位次 #3/7ACL 2026Findings· Findings of ACL
V iew- R 1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning
Minjie Hong · Zirun Guo · Jiabao Zhang · zehan wang · Ziang Zhang · Tao Jin · Zhou Zhao
摘要
Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but often struggle with complex reasoning. Reinforcement learning (RL) can enhance reasoning, yet it may cause performance degradation on general tasks and overthinking in MLLMs. We propose Asymmetric Policy Optimiz...