VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression

2026-08-22

AI Summary

本文提出VIG方法，通过衡量图像对推理标记的预测不确定性减少程度来压缩多模态链式思维，提高多模态推理模型的效率与准确性。

Abstract

Multimodal large reasoning models often rely on long Chain-of-Thought (CoT) traces in which a substantial fraction of tokens, such as repeated visual descriptions, self-reflection, and other visually-disengaged filler, inflate inference cost without contributing to the answer. Existing CoT compression methods optimize output length but never measure whether a reasoning token is actually grounded in the image. We propose \textbf{VIG} (Visual Information Gain), an information-theoretic GRPO reward that scores each reasoning token by how much the image reduces its predictive uncertainty. VIG is computed online from two forward passes of the same policy, one with and one without the image, so no reference chains, external annotations, or auxiliary reward models are needed. Across six main multimodal reasoning benchmarks and three Qwen3-VL-Thinking model sizes (2B/4B/8B), plus an additional R1-Onevision-Bench evaluation on 8B, VIG consistently improves the accuracy--efficiency trade-off, supporting our central claim: \emph{efficient multimodal reasoning emerges from raising visual information density, where every reasoning token earns its place by anchoring to the image, rather than from imposing a length budget.} Our source code is available at https://github.com/chaser682/vig.

Problem

• multimodal reasoning
• Chain-of-Thought
• inference cost
• visual information
• compression

Innovation

• Visual Information Gain
• Chain-of-Thought Compression
• Multimodal Reasoning