拆分全局规划与局部执行，让导航更稳定高效。
Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation
- 用两个智能体分别负责战略规划和实时操作，解耦复杂任务
- 在三个数据集上零样本测试提升4.9%~6.5%，长期导航更稳定
- 适合做长程导航、多智能体协作或大模型集成的项目参考
视觉-语言场景导航是人机协同中的基础能力，要求智能体根据自然语言指令在复杂环境中执行连贯动作序列。现有方法要么依赖多个智能体，带来高协调成本；要么采用单智能体架构，使智能体同时承担全局规划与局部感知，导致推理能力下降和指令漂移。为此，我们提出DACo——一种规划-定位解耦架构，通过全局指挥官进行高层战略规划，本地操作员负责本体观察与精细执行。该设计缓解认知过载，提升长程稳定性。框架还融合动态子目标规划与自适应重规划，实现结构化且鲁棒的导航。在R2R、REVERIE和R4R上的实验表明，DACo在零样本设置下相比最优基线绝对提升4.9%、6.5%、5.4%，并能有效泛化至闭源（如GPT-4o）与开源（如Qwen-VL系列）模型。DACo为鲁棒长程导航提供了一个原则性且可扩展的新范式。
原文摘要 · Abstract (English)
Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI collaboration, requiring agents to follow natural language instructions to execute coherent action sequences in complex environments. Existing approaches either rely on multiple agents, incurring high coordination and resource costs, or adopt a single-agent paradigm, which overloads the agent with both global planning and local perception, often leading to degraded reasoning and instruction drift in long-horizon settings. To address these issues, we introduce DACo, a planning-grounding decoupled architecture that disentangles global deliberation from local grounding. Concretely, it employs a Global Commander for high-level strategic planning and a Local Operative for egocentric observing and fine-grained execution. By disentangling global reasoning from local action, DACo alleviates cognitive overload and improves long-horizon stability. The framework further integrates dynamic subgoal planning and adaptive replanning to enable structured and resilient navigation. Extensive evaluations on R2R, REVERIE, and R4R demonstrate that DACo achieves 4.9%, 6.5%, 5.4% absolute improvements over the best-performing baselines in zero-shot settings, and generalizes effectively across both closed-source (e.g., GPT-4o) and open-source (e.g., Qwen-VL Series) backbones. DACo provides a principled and extensible paradigm for robust long-horizon navigation. Project page: https://github.com/ChocoWu/DACo
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。