Learning When to Think in Latent Visual Space: Reasoning Mode Adaptive Reinforcement Learning
Abstract
AbstractLatent Visual Reasoning (LVR) unfolds reasoning in a continuous visual embedding space, markedly improving Vision-Language Models (VLMs) on vision-intensive tasks. However, our experiments reveal a hidden cost: LVR inevitably undermines VLMs’ strong textual reasoning ability, causing substantial degradation on logic-intensive tasks. This motivates us to unify both reasoning modes within a single VLM that adaptively selects the appropriate one. We propose MoLaT (Mixture of Latent and Textual Reasoning), a novel method that trains VLMs via reinforcement learning (RL) to select LVR and text-only reasoning adaptively. MoLaT is trained in two stages. Supervised fine-tuning endows the VLM with a dual-mode capability using mixed CoT data. Then, MoLaT introduces two complementary designs: 1) The mode-adaptive advantage decouples the mode-selection signal from per-rollout correctness reward at the token level: mode-selection tokens receive dedicated cross-mode gradients, while content tokens retain the group-relative advantage. 2) The entropy-modulated advantage weight uses sequence-level entropy as a difficulty proxy, modulating signal strength to prevent premature mode commitment. Experiments confirm that MoLaT improves both vision-intensive and logic-intensive abilities, validating adaptive mode selection as key to general-purpose reasoning VLMs.