感知以假设，验证以落地：面向开放世界地理定位的智能体推理框架

中文摘要 AI 辅助

开放世界地理定位要求模型通过多步推理和外部知识落地来对模糊的视觉线索进行推理。尽管近期的大型视觉语言模型展现出强大的多模态推理能力，但现有方法仍因缺乏基于明确证据的验证而存在感知幻觉和上下文漂移问题。本研究将地理定位重新表述为类似人类的感知后验证推理问题，并提出GeoPAVE（地理定位感知与验证引擎），这是一个双层智能体框架，包含通过单次前向传播生成的基于感知的假设，以及针对决策动作（支持、反驳、弃权（不执行））的基于验证的证据落地。为支持严格评估，我们进一步引入PAVED，这是一个源自真实世界用户签到数据的新型数据集，配备了包含多跳查询、多轮工具调用和结构化感知验证轨迹的完整推理路径。该数据集和代码可在httpsURL获取。

英文摘要

Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While recent large vision-language models exhibit strong multimodal reasoning capabilities, existing approaches still suffer from perceptual hallucination and context drift due to the lack of explicit evidence-grounded verification. In this work, we reformulate geo-localization as a human-like perceive-then-verify reasoning problem and propose GeoPAVE (Geo-localization Perception-and-Verification-Engine), a bi-level agentic framework that contains perception-based hypothesis generation via single-pass rollouts and verification-based evidence grounding for decision actions: support, refute, and refine. To support rigorous evaluation, we further introduce PAVED, a novel dataset derived from real-world user check-in data, equipped with comprehensive reasoning trajectories featuring multi-hop queries, multi-round tool invocations, and structured perception-verification traces. The dataset and code are available at https://github.com/Arandinglv/GeoPAVE.

发表机构

• The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
• The Hong Kong University of Science and Technology（香港科技大学）

机构由 AI 辅助整理，请以论文原文为准。