发表机构
Beijing University of Posts and Telecommunications; Hunan Normal University（北京邮电大学; 湖南师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出HiRS-Agent分层多智能体系统，通过两层协作架构与优化策略，在Earth-Agent Benchmark和ThinkGeo上提升了长时程遥感任务的工具使用能力与正确性。
AI 中文摘要
近期，大型语言模型与多模态模型的进展推动遥感（RS）处理从简单感知模型转向用于解决复杂长时程遥感任务的智能体系统。然而，现有系统常依赖单一决策框架，无法适配遥感任务多阶段、相互依赖的特性，这种集中式方法会导致任务执行不稳定、工具使用错误、错误跨阶段传播等问题。为解决这些问题，本文提出HiRS-Agent，一种用于长时程遥感任务解决的分层多智能体系统。HiRS-Agent采用两层协作架构：管理层负责动态路由、步骤级验证、重新规划及终止控制；专家层根据遥感工作流程组织领域特定工具，负责子任务推理与工具执行。为进一步提升系统能力，本文引入两阶段监督微调策略与验证引导的分层强化学习阶段，共同优化协作与工具使用策略。在Earth-Agent Benchmark与ThinkGeo上的实验表明，HiRS-Agent显著提升了长时程工具使用能力与最终任务正确性，证明了结构化多智能体协作对可靠遥感智能体的有效性，代码公开于此链接。
英文摘要
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.
CommentsAccepted at ACM Multimedia 2026 (MM '26)
