让导航模型按需推理，减少无效计算，提升长程导航准确率。
AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation
- 根据动作不确定性动态触发推理，避免固定步长的低效
- 仅用6000样本训练，就超越百万数据训练的闭源模型
- 适合资源受限的智能体，尤其适用于真实场景导航
视觉语言导航（VLN）要求智能体在长时序视觉观测中理解自然语言指令并执行动作。显式推理可增强时间一致性与感知-动作对齐，但固定步长推理常导致性能不佳且计算冗余。为此，我们提出AdaNav，一种基于不确定性的自适应推理框架。核心是轻量级的不确定性自适应推理模块（UAR），能动态决定是否触发推理。引入动作熵作为策略先验，并通过启发式到强化学习的训练方法逐步优化，使智能体在具身任务数据稀缺的条件下学会感知任务难度并制定合理推理策略。实验表明，仅使用6000个训练样本，AdaNav在R2R val-unseen上成功率提升20%，在RxR-CE上提升11.7%，真实场景下提升11.4%。代码已开源。
原文摘要 · Abstract (English)
Vision Language Navigation (VLN) requires agents to follow natural language instructions by grounding them in sequential visual observations over long horizons. Explicit reasoning could enhance temporal consistency and perception action alignment, but reasoning at fixed steps often leads to suboptimal performance and unnecessary computation. To address this, we propose AdaNav, an uncertainty-based adaptive reasoning framework for VLN. At its core is the Uncertainty Adaptive Reasoning Block (UAR), a lightweight plugin that dynamically triggers reasoning. We introduce Action Entropy as a policy prior for UAR and progressively refine it through a Heuristics to RL training method, enabling agents to learn difficulty aware reasoning policies under the strict data limitations of embodied tasks. Results show that with only 6K training samples, AdaNav achieves substantial gains over closed source models trained on million scale data, improving success rate by 20% on R2R val-unseen, 11.7% on RxR-CE, and 11.4% in real world scenes. The code is available at https://github.com/xinding-sys/AdaNav.
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。