基于地图的思考：用于地理定位的强化并行地图增强智能体
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
AI总结：
本文提出基于地图的强化并行智能体，通过两阶段优化提升地理定位精度，实验显示在Acc@500m指标上显著优于现有模型。
摘要：
图像地理定位任务旨在利用视觉线索预测图像拍摄的地球位置。现有的大型视觉-语言模型（LVLM）方法利用世界知识、推理链和智能体能力，但忽视了人类常用的一种策略——使用地图。在本文中，我们首先为模型配备了“基于地图的思考”能力，并将其公式化为地图循环中的智能体。我们为此开发了两阶段优化方案，包括智能体强化学习（RL）后接并行测试时间扩展（TTS）。RL增强了模型的智能体能力以提高采样效率，而并行TTS使模型能够在最终预测前探索多个候选路径，这对于地理定位至关重要。为了在最新和真实世界图像上评估我们的方法，我们进一步提出了MAPBench，一个由完全真实世界图像组成的综合地理定位训练和评估基准。实验结果表明，我们的方法在大多数指标上优于现有的开源和闭源模型，特别是将Acc@500m从8.0%提升到22.1%，相比Google Search/Map grounded模式下的Gemini-3-Pro。
英文摘要：
The image geolocalization task aims to predict the location where an image was taken anywhere on Earth using visual clues. Existing large vision-language model (LVLM) approaches leverage world knowledge, chain-of-thought reasoning, and agentic capabilities, but overlook a common strategy used by humans -- using maps. In this work, we first equip the model \textit{Thinking with Map} ability and formulate it as an agent-in-the-map loop. We develop a two-stage optimization scheme for it, including agentic reinforcement learning (RL) followed by parallel test-time scaling (TTS). The RL strengthens the agentic capability of model to improve sampling efficiency, and the parallel TTS enables the model to explore multiple candidate paths before making the final prediction, which is crucial for geolocalization. To evaluate our method on up-to-date and in-the-wild images, we further present MAPBench, a comprehensive geolocalization training and evaluation benchmark composed entirely of real-world images. Experimental results show that our method outperforms existing open- and closed-source models on most metrics, specifically improving Acc@500m from 8.0\% to 22.1\% compared to \textit{Gemini-3-Pro} with Google Search/Map grounded mode.
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。
