外观
论文arXiv 2610.0491624 天前
PreAct-Nav：城市导航中的行动前智能体推理
原文链接：PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation（arXiv 2610.04916 · 发布日期：2026-10-04）
PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation
为解决远目标难以转为局部决策，PreAct-Nav用记忆与预测推理增强冻结策略，并在城市导航评估中验证。
核心要点
- 城市导航需由自我中心观察完成长程目标，现有方法难以形成连贯局部决策。
- 框架以持续的中期子目标锚定决策，并用导航记忆维护子目标与相关经验。
- 预测世界沙盒用AC-WM预测候选动作后果，VLM据当前子目标保留或修正动作。
- 评估显示记忆更新和视觉预测改进行动选择，长路线和多转弯路线收益更明显。
英文摘要 (Abstract)
Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agentic navigation methods often struggle to translate distant goals into coherent local decisions in large-scale physical environments. Their reliance on linguistic reasoning over transient observations or limited history constrains anticipation of the consequences of actions and future conditions, despite the importance of such foresight for navigating long and complex urban routes. To bridge this gap, we propose PreAct-Nav, an agentic navigation framework that equips frozen policies with anticipatory reasoning for robust urban navigation. Our central idea is to anchor local decisions in persistent medium-horizon subgoals, assess the consequences of predicted actions before execution, and continually update the reasoning context using actual outcomes. At its core, a navigation memory module maintains the active subgoal and relevant experience across decisions, translating distant goals into actionable intermediate objectives. We further introduce a predictive world sandbox that uses an action-conditioned world model (AC-WM) to forecast world dynamics conditioned on candidate movements. A vision-language model (VLM) reasoner interprets these predictions under the current subgoal to retain or revise actions. After execution, real observations are used to assess outcomes, correct inconsistent assumptions, and update memory to continue or reformulate the subgoal. Extensive evaluations demonstrate that the proposed PreAct-Nav improves action selection through memory updates and visual prediction, with more pronounced gains on longer routes and routes with more turns.
作者：Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Junwei Yang, Songchang Jin, Dianxi Shi
来源
本页事实对应的公开页面，以原文为准。