NavHarness：迈向终身具身导航
NavHarness: Towards Lifelong Embodied Navigation
浏览论文内容
中文总结 AI 辅助
NavHarness提出一种无需训练的终身具身导航框架，将记忆处理纳入导航循环，通过跨会话经验传递和结构化恢复交接，在GOAT-Bench和IR2R-CE上显著提升成功率，证明连续推理会话对终身导航至关重要。
中文摘要 AI 辅助
前沿模型现在可以通过多轮多模态推理和简单工具在单个具身导航任务上表现出色。然而，在连续任务中，智能体还必须依赖不断更新的地图和早期的搜索记录，这两者都可能不完整或与新的观察结果冲突。我们提出了NavHarness，一种无需训练的具身导航框架，旨在实现终身导航，它将记忆处理纳入导航循环。在导航过程中，其多轮智能体会话利用地图、任务记录和房屋知识，将其与观察结果进行核对，并记录修正以指导其行动。NavHarness将这种经验跨新对话保留下来，用于新任务或恢复尝试，而结果验证和运行结束摘要支持其后续重用。在GOAT-Bench上，NavHarness在Astra上将s-SR比仅上下文独立会话提高了18.6个百分点，在Opus 5上提高了22.6个百分点。使用SLAM估计的位姿，配备GPT-6 Astra的NavHarness在GOAT-Bench上实现了83.7 s-SR和36.9 e-SR的最先进任务成功率，在IR2R-CE上实现了85.9 s-SR。为了理解这些增益，我们检查了经验如何在会话之间传递，发现结构化恢复交接优于长度匹配的摘要。在跨房屋的扩展部署中，整合在保留地图和任务记录的基础上进一步改善了导航，案例研究显示智能体如何利用早期经验来解释新目标、调查未解决的问题并恢复失败的搜索。我们认为，迈向终身导航的进展取决于连续推理会话如何建立在先前经验之上，以及单任务能力的改进。
英文摘要
Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools. Across successive tasks, however, an agent must also rely on an evolving map and earlier search records, both of which may be incomplete or conflict with new observations. We present NavHarness, a training-free embodied harness towards lifelong navigation that makes memory processing part of the navigation loop. During navigation, its multi-round agentic session draws on maps, task records, and house knowledge, checking them against observations and recording corrections to guide its actions. NavHarness preserves this experience across fresh conversations for new tasks or recovery attempts, while outcome verification and run-end summaries support its later reuse. On GOAT-Bench, NavHarness improves s-SR over context-only independent sessions by 18.6 points with Astra and 22.6 with Opus 5. Using SLAM-estimated poses, NavHarness with GPT-6 Astra achieves state-of-the-art task success of 83.7 s-SR with 36.9 e-SR on GOAT-Bench and 85.9 s-SR on IR2R-CE. To understand these gains, we examine how experience is carried between sessions and find that structured recovery handovers outperform length-matched summaries. In extended deployments across houses, consolidation improves navigation beyond retaining maps and task records, with case studies showing how agents use earlier experience to interpret new goals, investigate unresolved questions, and resume failed searches. We suggest that progress towards lifelong navigation depends on how successive reasoning sessions build on prior experience, alongside improvements in single-task capability.
