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. The code and dataset are publicly available at https://lennoxdai.github.io/EndoCoT-Webpage/.

翻译：近年来，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来处理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，而该过程对于 MLLMs 为复杂任务提供准确指导至关重要。（ii）指导在解码过程中保持不变。解码过程中的不变指导阻碍了 DiT 将复杂指令逐步分解为可执行去噪步骤，即使获得了正确的 MLLM 编码。为此，我们提出内生思维链（EndoCoT），这是一个新颖的框架，首先通过迭代思维指导模块迭代优化潜在思维状态，从而激活 MLLMs 的推理潜力，然后将这些状态桥接到 DiT 的去噪过程中。其次，应用终端思维锚定模块，通过将最终状态与真实答案对齐，确保推理轨迹始终基于文本监督。通过这两个组件，MLLM 文本编码器提供经过精细推理的指导，使 DiT 能够逐步执行该指导，最终以分步方式解决复杂任务。在多样化基准测试（例如 Maze、TSP、VSP 和 Sudoku）上的广泛评估实现了 92.1% 的平均准确率，优于最强基线 8.3 个百分点。代码和数据集已在 https://lennoxdai.github.io/EndoCoT-Webpage/ 公开提供。