ProFocus：视觉语言导航中的主动感知与聚焦推理
ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
将全景观测转成结构化自我中心语义地图，并由 LLM 编排智能体主动发起带焦点区域的视觉查询，这一「主动感知 + 定向取景」的闭环可直接迁移到任何需要从冗余全景/多视角输入中按需取景的具身导航或主动视觉任务；BD-MCTS 从大量历史候选中筛出 top-k 高价值路点再做聚焦推理，也为长时序视觉历史的高效利用提供了可复用策略。
原文依据 ProFocus transforms panoramic observations into structured ego-centric semantic maps, enabling the orchestration agent to identify missing visual information
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉语言导航（VLN）要求智能体准确感知复杂的视觉环境，并对导航指令与历史进行推理。然而，现有方法被动地处理冗余的视觉输入，并不加区分地对待所有历史上下文，导致感知效率低下、推理缺乏聚焦。为应对这些挑战，我们提出 ProFocus，一个免训练（training-free）的渐进式框架，通过大语言模型（LLM）与视觉语言模型（VLM）之间的协作，将主动感知与聚焦推理统一起来。在主动感知方面，ProFocus 将全景观测转换为结构化的自我中心语义地图，使编排智能体能够识别可靠决策所需的缺失视觉信息，并生成带有相应焦点区域的定向视觉查询，以引导感知智能体获取所需的观测。在聚焦推理方面，我们提出分支多样化蒙特卡洛树搜索（BD-MCTS），从大量历史候选中识别出 top-k 高价值路点。决策智能体将推理聚焦于与这些路点相关联的历史上下文，而非同等对待所有历史路点。大量实验验证了 ProFocus 的有效性，在 R2R 与 REVERIE 基准上取得了零样本方法中的最优性能。
英文原文摘要 1412 字符
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 ProFocus, a training-free progressive framework that unifies Proactive Perception and Focused 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.