HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving
2026-08-31 • Artificial Intelligence
Artificial IntelligenceMultiagent SystemsMultimedia
AI summaryⓘ
The authors present HiRS-Agent, a new system for handling complex remote sensing tasks by using multiple agents working together instead of one central decision-maker. Their design splits the work into a Manager Layer that oversees the process and a Specialist Layer that focuses on specific subtasks. They also introduce training methods to help the agents coordinate better and use tools more effectively. Tests show that their system improves how reliably these tasks are completed over long periods.
remote sensinglarge language modelsmultimodal modelshierarchical multi-agent systemlong-horizon taskstool-use policiesreinforcement learningsupervised tuningtask decompositionworkflow management
Authors
Boyang Mu, Zhiwei Wei, Mugen Peng, Wenjia Xu
Abstract
Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent.