Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning

arXiv:2610.15810v1 Announce Type: new Abstract: The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on general and reasoning tasks. However, existing fast-slow reasoning paradigms mainly regulate textual reasoning length, while visual computation introduced by external tools or visual tokens is often treated as an auxiliary component. This separation prevents MLLMs from jointly optimizing visual perception and textual reasoning. To address this issue, we propose L2T (adaptive Look, flexible Thought), a unified reasoning framework that jointly optimizes the form and depth of computation. L2T first discretizes tool-produced visual states into visual tokens, bringing visual perception and textual reasoning into a shared autoregressive space. Based on this unified representation, L2T introduces a modality-aware routing reward to select appropriate reasoning modes and a difficulty-aware fast-slow strategy to adapt reasoning depth according to task complexity. Experiments on general perception and reasoning-intensive tasks demonstrate the effectiveness of L2T. Compared with explicit tool-calling approaches, L2T maintains competitive performance while achieving 1.7--3.6 times higher throughput.

Related

• Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning
• TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
• AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
• AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question Answering
• Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning

Source: arXiv cs.CV | 2026-10-14