Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

2026-06-21

AI Summary

The effectiveness boundaries of multimodal Chain-of-Thought (CoT) reasoning remain unclear. This study systematically evaluates 12 tasks, comparing 14 non-reasoning and 8 reasoning-based multimodal large language models. It reveals that CoT enhances performance in mathematical, scientific, and multi-image reasoning tasks, yet degrades accuracy in perceptual tasks such as visual grounding and counting. The analysis identifies a pervasive “vision-light, reasoning-heavy” tendency—where visual information is progressively downweighted during reasoning—as a key bottleneck in multimodal CoT. Furthermore, the findings indicate that current open-source models exhibit limited overall improvement on such reasoning tasks, highlighting a critical gap in effectively integrating perception with structured reasoning.

Abstract

Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key question: What can multimodal Chain-of-Thought reasoning do, and where and why does it fall short? To this end, we evaluate 12 multimodal tasks across perception and reasoning categories using both 14 non-reasoning models and 8 reasoning models. Our analysis reveals several important findings: (1) CoT is not a free lunch and should be used selectively depending on the specific requirements of each task. For perception tasks, CoT can lead to undesirable side effects, such as reduced performance in visual grounding and object counting. In contrast, it proves effective for reasoning tasks involving mathematical, scientific, and multi-image reasoning; (2) Compared to original models, existing open-source multimodal reasoning models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities; (3) Visual reasoning remains a key bottleneck for current multimodal CoT, as models exhibit a Look Light, Think Heavy pattern where verbal reflection rises and falls during reasoning, whereas visual reflection consistently diminishes. These findings suggest that while multimodal CoT handles verbal reflection relatively well, it lacks the ability to maintain deep visual introspection throughout the reasoning process.

Problem

• Multimodal Chain-of-Thought
• visual reasoning
• perception tasks
• reasoning tasks
• visual grounding

Innovation

• Multimodal Chain-of-Thought
• Visual Reasoning
• Perception vs. Reasoning
• Look Light Think Heavy
• Multimodal LLMs