给机器人装了个“调度中枢”，不训练也能认路找东西
现在的具身导航AI分两派：一派靠大量训练，换个环境就失灵；另一派不训练、直接调大模型，但大模型只会“说”不会“核对”——它说往左走，可左边明明是墙，它也照走。这篇把不训练的路子往前推了一步：给AI加了一个“调度中枢”，像项目经理一样，把看、找、走、纠错、停这几件事拆开，每走一步都用空间证据和几何可行性去验证大模型的提议，不对就驳回重来。它还会把走过的路和失败原因记在一张“空间地图”上，下次路过就知道绕开。在四个标准测试里，成功率分别达到60.8%、53.9%、76.0%和59.3%，都超过了此前所有不训练的方法，而且真的装到了人形机器人上跑通了。它不是你明天能用上的东西，但它指向一个更靠谱的方向：与其逼大模型自己认路，不如给它配一个会查账的管家。
📄 原文摘要(英文)
Embodied navigation requires agents to interpret visual observations, accumulate spatial knowledge, and execute actions to follow instructions or locate objects. Training-based methods face generalization challenges, while training-free methods exploit multimodal large language models (MLLMs) but often lack mechanisms to reconcile proposed actions with spatial evidence, task progress, and execution failures. We present HarnessVLN, a zero-shot, training-free framework whose Agent Harness coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface. The Harness validates planner proposals against spatial evidence, geometric feasibility, and subgoal consistency, incorporating structured tool feedback into subsequent decisions. Hierarchical event memory tracks task progress and execution history, while a persistent Spatiotemporal Graph maintains reusable spatial evidence and failure annotations for verification and recovery. A replaceable Navigation Executor converts validated targets into executable motions, allowing the same Harness protocol to support instruction-following and object-goal navigation. HarnessVLN achieves success rates of 60.8%, 53.9%, 76.0%, and 59.3% on R2R, RxR, HM3D-v2, and HM3D-OVON, respectively, surpassing prior training-free SOTA results. Humanoid deployment further demonstrates its applicability to both tasks in real-world environments. The project page is: https://harnessvln.netlify.app/.