研究人员推出了TerraLogic，这是一个旨在评估地球观测任务中分层地理空间推理能力的新基准测试。该基准测试包含545个场景驱动的任务，涵盖了光学、合成孔径雷达（SAR）和红外（IR）等多种图像类型。为了应对这一基准测试的挑战，研究团队还开发了HieraPlan，这是一个工具增强型代理，能够将工具包组织成功能层次结构并执行容错推理。实验表明，现有方法在这种推理方面存在困难，而HieraPlan提供了一个有希望的基线。 AI
影响 该基准测试和代理有望在复杂地理空间分析中提升AI能力，应用于灾害评估和城市规划等领域。
排序理由 该集群描述了一个用于地理空间推理的新学术基准测试和代理，已在arXiv上发布。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large language models (LLMs) have enabled tool-augmented agents that leverage external tools to perform complex analytical tasks. However, e…
arXiv:2607.12497v1 Announce Type: new Abstract: Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large language models (LLMs) have enabled tool-augmented agents that leverage external tools…
Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large language models (LLMs) have enabled tool-augmented agents that leverage external tools to perform complex analytical tasks. However, e…