Saved in:
Bibliographic Details
Main Authors: Xu, Wenjia, Yu, Zijian, Mu, Boyang, Wei, Zhiwei, Zhang, Yuanben, Li, Guangzuo, Wang, Jiuniu, Peng, Mugen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.07089
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912891834204160
author Xu, Wenjia
Yu, Zijian
Mu, Boyang
Wei, Zhiwei
Zhang, Yuanben
Li, Guangzuo
Wang, Jiuniu
Peng, Mugen
author_facet Xu, Wenjia
Yu, Zijian
Mu, Boyang
Wei, Zhiwei
Zhang, Yuanben
Li, Guangzuo
Wang, Jiuniu
Peng, Mugen
contents The unprecedented advancements in Multimodal Large Language Models (MLLMs) have demonstrated strong potential in interacting with humans through both language and visual inputs to perform downstream tasks such as visual question answering and scene understanding. However, these models are constrained to basic instruction-following or descriptive tasks, facing challenges in complex real-world remote sensing applications that require specialized tools and knowledge. To address these limitations, we propose RS-Agent, an AI agent designed to interact with human users and autonomously leverage specialized models to address the demands of real-world remote sensing applications. RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning, enabling it to interpret user queries and orchestrate tools for accurate remote sensing task. We introduce two novel mechanisms: Task-Aware Retrieval, which improves tool selection accuracy through expert-guided planning, and DualRAG, a retrieval-augmented generation method that enhances knowledge relevance through weighted, dual-path retrieval. RS-Agent supports flexible integration of new tools and is compatible with both open-source and proprietary LLMs. Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and delivering superior performance in tasks such as scene classification, object counting, and remote sensing visual question answering. Our work presents RS-Agent as a robust and extensible framework for advancing intelligent automation in remote sensing analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07089
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
Xu, Wenjia
Yu, Zijian
Mu, Boyang
Wei, Zhiwei
Zhang, Yuanben
Li, Guangzuo
Wang, Jiuniu
Peng, Mugen
Computer Vision and Pattern Recognition
The unprecedented advancements in Multimodal Large Language Models (MLLMs) have demonstrated strong potential in interacting with humans through both language and visual inputs to perform downstream tasks such as visual question answering and scene understanding. However, these models are constrained to basic instruction-following or descriptive tasks, facing challenges in complex real-world remote sensing applications that require specialized tools and knowledge. To address these limitations, we propose RS-Agent, an AI agent designed to interact with human users and autonomously leverage specialized models to address the demands of real-world remote sensing applications. RS-Agent integrates four key components: a Central Controller based on large language models, a dynamic toolkit for tool execution, a Solution Space for task-specific expert guidance, and a Knowledge Space for domain-level reasoning, enabling it to interpret user queries and orchestrate tools for accurate remote sensing task. We introduce two novel mechanisms: Task-Aware Retrieval, which improves tool selection accuracy through expert-guided planning, and DualRAG, a retrieval-augmented generation method that enhances knowledge relevance through weighted, dual-path retrieval. RS-Agent supports flexible integration of new tools and is compatible with both open-source and proprietary LLMs. Extensive experiments across 9 datasets and 18 remote sensing tasks demonstrate that RS-Agent significantly outperforms state-of-the-art MLLMs, achieving over 95% task planning accuracy and delivering superior performance in tasks such as scene classification, object counting, and remote sensing visual question answering. Our work presents RS-Agent as a robust and extensible framework for advancing intelligent automation in remote sensing analysis.
title RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.07089