ProFocus：面向视觉-语言导航的前瞻性感知与聚焦推理
ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
AI总结：
ProFocus通过大语言模型与视觉-语言模型的协作，实现前瞻性感知和聚焦推理，提升视觉-语言导航任务的效率与准确性。
摘要：
视觉-语言导航（VLN）要求智能体准确感知复杂视觉环境并推理导航指令和历史。现有方法被动处理冗余视觉输入，导致感知低效和推理不聚焦。为此，我们提出ProFocus，一种无需训练的渐进框架，通过大语言模型（LLMs）和视觉-语言模型（VLMs）的协作，统一前瞻性感知与聚焦推理。前瞻性感知将全景观测转换为结构化的自身中心语义地图，使调度代理能识别所需缺失视觉信息并生成针对性视觉查询。聚焦推理中，我们提出分支多样蒙特卡洛树搜索（BD-MCTS）以识别高价值路径点，使决策代理聚焦于与这些路径点相关的上下文，而非同等对待所有历史路径点。大量实验验证了ProFocus的有效性，在R2R和REVERIE基准测试中实现了零样本方法的最先进性能。
英文摘要：
Vision-and-Language Navigation (VLN) requires agents to accurately perceive complex visual environments and reason over navigation instructions and histories. However, existing methods passively process redundant visual inputs and treat all historical contexts indiscriminately, resulting in inefficient perception and unfocused reasoning. To address these challenges, we propose \textbf{ProFocus}, a training-free progressive framework that unifies \underline{Pro}active Perception and \underline{Focus}ed Reasoning through collaboration between large language models (LLMs) and vision-language models (VLMs). For proactive perception, ProFocus transforms panoramic observations into structured ego-centric semantic maps, enabling the orchestration agent to identify missing visual information needed for reliable decision-making, and to generate targeted visual queries with corresponding focus regions that guide the perception agent to acquire the required observations. For focused reasoning, we propose Branch-Diverse Monte Carlo Tree Search (BD-MCTS) to identify top-$k$ high-value waypoints from extensive historical candidates. The decision agent focuses reasoning on the historical contexts associated with these waypoints, rather than considering all historical waypoints equally. Extensive experiments validate the effectiveness of ProFocus, achieving state-of-the-art performance among zero-shot methods on R2R and REVERIE benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
