An LLM-based multi-agent system for remote sensing analysis

Мультиагентная система на основе большой языковой модели для анализа данных дистанционного зондирования
Jun Yang, Jun Yang, Zhelun Sun, Yuyu Zhou
2026-01-08

AI-driven task planningAutoGenlarge language modelsmulti-agent systemsremote sensing analysis
Remote sensing analysis converts remotely sensed data into actionable insights across diverse fields. However, traditional data-driven approaches frequently overlook the technical challenges encountered by end-users lacking remote sensing expertise. To address this issue, we proposed a multi-agent system framework based on a large language model, designed to facilitate remote sensing analysis for non-experts. The framework consists of three main modules: Data, which includes remote sensing datasets and supplementary information; Tools, encompassing algorithms and visualization tools; and Brain, which provides AI-driven task management and reasoning. We employed a prototype system called ExpertsRS, developed on the AutoGen framework and DeepSeek-V3, to validate the proposed framework. This prototype features three LLM-powered agents with distinct roles and functionalities, collaborating to fulfill user requests. The system was evaluated through two experiments. The first experiment demonstrated that ExpertsRS could translate ambiguous queries into structured analytical workflows and produce outputs comparable to those of human experts. The second experiment indicated that ExpertsRS outperformed both a baseline LLM and a single-agent configuration in planning efficiency and result accuracy, with only a modest increase in token usage. Our system underscores the potential of large language model-based multi-agent system to assist end-users in overcoming technical barriers in remote sensing analysis.
1
ExpertsRS outperformed both a baseline LLM and a single-agent configuration in planning efficiency and result accuracy, requiring only a modest increase in token usage.
2
ExpertsRS translated ambiguous user queries into structured analytical workflows and generated outputs comparable to those produced by human experts.
3
The ExpertsRS prototype uses three role-specialized LLM agents built with AutoGen and DeepSeek-V3 to collaboratively fulfill user requests.
4
The framework integrates three modules: remote sensing data and supplementary information, analytical and visualization tools, and AI-driven task management and reasoning.
5
The paper introduces an LLM-based multi-agent framework that enables non-experts to perform remote sensing analysis despite technical barriers.

LLM-based multi-agent system for remote sensing analysis

facilitation of non-expert remote sensing analysis through task management, workflow planning, reasoning, and accurate results

Publication Details
Publication Date
2026-01-08
Journal
Publisher
ISSN
Cited by
6
Access Type
Author Information
Authors
Jun Yang
Jun Yang
Zhelun Sun
Yuyu Zhou
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%