DA-CoT：训练免费难度感知思维链方法降低多模态模型过度思考
Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation
研究团队发现 CoT 用多了反而掉分，提出用注意力熵判断何时才需要思考，免训练就在推理分割基准上拿了 SOTA，还更省算力。
论文提出 Difficulty-Aware Chain-of-Thought（DA-CoT），一种免训练的自适应框架。研究发现多模态大语言模型中不加区分地使用 CoT 会引发过度思考（overthinking），导致推理分割任务中查询意图与视觉定位错位。方法利用模型注意力图的熵作为难度信号：低熵表示定位自信、无需 CoT，高熵则触发 CoT 推理。还引入 Bidirectional Rethinking 机制，在初始输出失败时自动翻转推理决策。DA-CoT 在 Reasoning Segmentation 基准上取得 SOTA，同时显著提升推理效率。
Attention Maps Know When to Think: Training-Free Difficulty-Aware Chain-of-Thought for Reasoning Segmentation
Chain-of-Thought (CoT) prompting has become a standard reasoning strategy in Multi-modal Large Language Models (MLLMs), showing strong performance in complex vision-language tasks such as reasoning segmentation. However, our analysis reveals that indiscriminate CoT usage can lead to degraded performance by inducing unnecessary reasoning, a phenomenon we term overthinking. In reasoning segmentation, overthinking often leads to misalignment between the query's intent and visual grounding. To address this, we propose Difficulty-Aware Chain-of-Thought (DA-CoT), a training-free adaptive framework that selectively triggers CoT based on the input's intrinsic difficulty. We find that the entropy of the model's attention maps reliably reflects task difficulty: low entropy indicates confident, localized grounding, while high entropy suggests uncertainty and potential benefit from CoT. DA-CoT uses this entropy signal to determine whether to apply CoT prompting. Additionally, we introduce a Bidirectional Rethinking mechanism that enables the model to automatically flip its reasoning decision when the initial output fails, enhancing robustness by recovering from failures induced by overthinking and underthinking. DA-CoT demonstrates its effectiveness by achieving state-of-the-art performance on the Reasoning Segmentation benchmarks while significantly improving inference efficiency.
