2026
Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
ICLR 2026poster
Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, po…