论文/arXiv 2607.12680·3 个月前

ReflectVLN：用反思式推理训练视觉-语言导航智能体

ReflectVLN通过意图与执行智能体的闭环交互和Action-CoT，在标准VLN基准上提升成功率与路径效率。

AI 整理

• 感知与导航
• 具身模型
• 端侧部署

原文链接：ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning（arXiv 2607.12680 · 发布日期：2026-07-14）

ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning

ReflectVLN通过意图与执行智能体的闭环交互和Action-CoT，在标准VLN基准上提升成功率与路径效率。

核心要点

• 现有VLN方法缺少显式闭环，难以跟踪语义进展、诊断失败并从长程误差中恢复。
• 框架以双向交互的意图智能体和执行智能体组织决策，按需反思并更新子任务。
• Action-CoT采用路径条件的双查询训练，使动作生成更具时间一致性并提供可解释中间理由。
• 实验显示在受限数据预算下提高成功率和路径效率，训练成本有利且推理时高层意图调用更少；代码已开源。

验证范围与局限：验证范围为标准VLN基准实验，摘要未说明真机验证。

英文摘要 (Abstract)

Existing vision-language navigation methods often couple a VLM with waypoint decoders to produce multi-step action plans, but they typically lack an explicit closed-loop mechanism for tracking semantic progress, diagnosing execution failures, and recovering from error accumulation in long-horizon navigation. To address this gap, we propose ReflectVLN, an agentic VLN framework that organizes decision-making through bidirectionally interactive intention and execution agents. The intention agent performs subtask decomposition and reflection, generating executable subtask descriptions as corrective plans. Conditioned on these descriptions, the execution agent grounds them into short-horizon actions under current observations while monitoring sub-goal progress and detecting off-track behavior. Crucially, ReflectVLN enables closed-loop bidirectional communication: the execution agent emits progress and deviation signals to trigger reflection and subtask updates on demand, and the intention agent returns structured guidance that reconditions subsequent actions for recovery. To encourage temporally coherent decisions with interpretable intermediate rationales, we introduce Action Chain-of-Thought (Action-CoT), a path-conditioned dual-query training scheme for action generation. Experiments on standard VLN benchmarks show that ReflectVLN improves success rates and path efficiency under a constrained data budget, with favorable training cost and fewer high-level intention calls at inference time, while providing interpretable intermediate decisions for analysis and collaboration. Code is available at: https://github.com/AIprogrammer/ReflectVLN

作者：Jiahang Wang, Yirong Yang, Yanqing Zhu, Minghua Luo, Shichao Xie, Fei Liu, Mu Xu

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2607.12680：ReflectVLN: Training Vision-Language Navigation Agents with Reflective Reasoning访问 2026-10-21