Embodied agents face a critical dilemma that end-to-end models lack interpretability and explicit 3D reasoning, while modular systems ignore cross-component interdependencies and synergies. To bridge this gap, we propose the Dynamic 3D Vision-Language-Planning Model (D3D-VLP). Our model introduces two key innovations: 1) A Dynamic 3D Chain-of-Thought (3D CoT) that unifies planning, grounding, navigation, and question answering within a single 3D-VLM and CoT pipeline; 2) A Synergistic Learning from Fragmented Supervision (SLFS) strategy, which uses a masked autoregressive loss to learn from massive and partially-annotated hybrid data. This allows different CoT components to mutually reinforce and implicitly supervise each other. To this end, we construct a large-scale dataset with 10M hybrid samples from 5K real scans and 20K synthetic scenes that are compatible with online learning methods such as RL and DAgger. Our D3D-VLP achieves state-of-the-art results on multiple benchmarks, including Vision-and-Language Navigation (R2R-CE, REVERIE-CE, NavRAG-CE), Object-goal Navigation (HM3D-OVON), and Task-oriented Sequential Grounding and Navigation (SG3D). Real-world mobile manipulation experiments further validate the effectiveness.

翻译：具身智能体面临一个关键困境：端到端模型缺乏可解释性与显式的三维推理能力，而模块化系统则忽视了跨组件间的相互依赖与协同效应。为弥合这一差距，我们提出了动态三维视觉-语言-规划模型（D3D-VLP）。该模型引入两项关键创新：1）动态三维思维链（3D CoT），将规划、定位、导航与问答统一于单一的三维视觉-语言模型与思维链流程中；2）碎片化监督协同学习策略（SLFS），通过掩码自回归损失从大规模部分标注的混合数据中学习，使不同思维链组件能够相互增强并实现隐式监督。为此，我们构建了一个包含1000万混合样本的大规模数据集，数据来源于5000个真实扫描场景与20000个合成场景，兼容强化学习与DAgger等在线学习方法。D3D-VLP在多项基准测试中取得了最先进的性能，包括视觉与语言导航（R2R-CE、REVERIE-CE、NavRAG-CE）、目标导向导航（HM3D-OVON）以及任务导向序列定位与导航（SG3D）。真实世界移动操作实验进一步验证了其有效性。