paper-with-me

Papers

Multi-Agent Geospatial Copilots for Remote Sensing Workflows

2025-01-27 · Chaehong Lee, Varatheepan Paramanayakam, Andreas Karatzas, Yanan Jian, Michael Fore, Heming Liao, Fuxun Yu, Ruopu Li, Iraklis Anagnostopoulos, Dimitrios Stamoulis

We present GeoLLM-Squad, a geospatial Copilot that introduces the novel multi-agent paradigm to remote sensing (RS) workflows. Unlike existing single-agent approaches that rely on monolithic large language models (LLM), GeoLLM-Squad separates agentic orchestration from geospatial task-solving, by delegating RS tasks to specialized sub-agents. Built on the open-source AutoGen and GeoLLM-Engine frameworks, our work enables the modular integration of diverse applications, spanning urban monitoring, forestry protection, climate analysis, and agriculture studies. Our results demonstrate that while single-agent systems struggle to scale with increasing RS task complexity, GeoLLM-Squad maintains robust performance, achieving a 17% improvement in agentic correctness over state-of-the-art baselines. Our findings highlight the potential of multi-agent AI in advancing RS workflows.

📄 PDF Abstract BibTeX arXiv:2501.16254

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems

2026-01-05 · Niloufar Alipour Talemi, Julia Boone, Fatemeh Afghah arxiv

The paradigm of Earth Observation analysis is shifting from static deep learning models to autonomous agentic AI. Although recent vision foundation models and multimodal large language models advance representation learn…

Representation Learning

GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots

2024-04-23 · Simranjit Singh, Michael Fore, Dimitrios Stamoulis

Geospatial Copilots unlock unprecedented potential for performing Earth Observation (EO) applications through natural language instructions. However, existing agents rely on overly simplified single tasks and template-ba…

Earth Observation

Agentic AI for Remote Sensing: Technical Challenges and Research Directions

2026-04-27 · Muhammad Akhtar Munir, Muhammad Umer Sheikh, Akashah Shabbir, Muhammad Haris Khan 외 arxiv

Earth Observation (EO) is moving beyond static prediction toward multi-step analytical workflows that require coordinated reasoning over data, tools, and geospatial state. While foundation models and vision-language mode…

Representation Learning

A Training-free, One-shot Detection Framework For Geospatial Objects In Remote Sensing Images

2019-04-04 · Tengfei Zhang, Yue Zhang, Xian Sun, Menglong Yan 외

Deep learning based object detection has achieved great success. However, these supervised learning methods are data-hungry and time-consuming. This restriction makes them unsuitable for limited data and urgent tasks, es…

Objectobject-detectionObject Detection

TorchGeo: Deep Learning With Geospatial Data

2021-11-17 · Adam J. Stewart, Caleb Robinson, Isaac A. Corley, Anthony Ortiz 외

Remotely sensed geospatial data are critical for applications including precision agriculture, urban planning, disaster monitoring and response, and climate change research, among others. Deep learning methods are partic…

Deep LearningTransfer Learning