EndoCoT：扩散模型中内生思维链推理的规模化实现

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

March 12, 2026

作者: Xuanlang Dai, Yujie Zhou, Long Xing, Jiazi Bu, Xilin Wei, Yuhong Liu, Beichen Zhang, Kai Chen, Yuhang Zang

cs.AI

摘要

近期，多模态大语言模型（MLLMs）被广泛集成到扩散框架中，主要作为文本编码器以解决空间推理等复杂任务。然而，该范式存在两个关键局限：（i）MLLMs文本编码器的推理深度不足。单步编码无法激活思维链过程，而该过程对MLLMs为复杂任务提供精准指导至关重要；（ii）指导信号在解码过程中保持恒定。即使MLLM编码正确，这种恒定指导也会阻碍扩散变换模型（DiT）将复杂指令逐步分解为可执行的去噪步骤。为此，我们提出内生思维链（EndoCoT）——一种通过迭代思维指导模块精炼潜在思维状态以激活MLLMs推理潜力，并将这些状态与DiT去噪过程相连接的新型框架。其次，通过终端思维锚定模块将最终状态与真实答案对齐，确保推理轨迹始终受文本监督的约束。借助这两个组件，MLLM文本编码器可提供精细推理的指导信号，使DiT能够逐步执行并最终以分步方式解决复杂任务。在多样化基准测试（如迷宫、旅行商问题、车辆路径问题和数独）上的大量实验表明，该方法平均准确率达92.1%，较最强基线提升8.3个百分点。

English

Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from two critical limitations: (i) MLLMs text encoder exhibits insufficient reasoning depth. Single-step encoding fails to activate the Chain-of-Thought process, which is essential for MLLMs to provide accurate guidance for complex tasks. (ii) The guidance remains invariant during the decoding process. Invariant guidance during decoding prevents DiT from progressively decomposing complex instructions into actionable denoising steps, even with correct MLLM encodings. To this end, we propose Endogenous Chain-of-Thought (EndoCoT), a novel framework that first activates MLLMs' reasoning potential by iteratively refining latent thought states through an iterative thought guidance module, and then bridges these states to the DiT's denoising process. Second, a terminal thought grounding module is applied to ensure the reasoning trajectory remains grounded in textual supervision by aligning the final state with ground-truth answers. With these two components, the MLLM text encoder delivers meticulously reasoned guidance, enabling the DiT to execute it progressively and ultimately solve complex tasks in a step-by-step manner. Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points.