SkillEarth：通过技能进化让通用智能体掌握遥感工具调用
SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution
做遥感智能体的团队可以看看这篇：它把工具调用经验存成可复用的技能文件，换了底层模型也不用重训，靠真实工具链执行加双裁判反馈来打磨。和现有靠结果反思改技能的方法比，修正粒度细到组件级。用 LLM 搭遥感工作流的开发者值得关注。
SkillEarth 是一种自进化技能抽取方法，把遥感工具调用知识外化为可复用、可检索、可演化的技能文件，无需专家干预或参数更新即可从示范轨迹中自动抽取。它在 OpenEarth-Bench 和 Earth-Bench 两个基准上验证，工具选择、参数正确性、执行顺序一致性和任务完成度均超过现有遥感智能体与技能抽取方法。
技术机制上，SkillEarth 把技能进化锚定在真实工具链执行上，结合双裁判反馈与观测锚定的路由图，实现组件级精细修正，区别于依赖结果反思的整体性修正方法。
实验覆盖 3 个前沿 LLM 和 4 个开源 LLM，抽取的技能支持跨模型复用而无需重训练。相比依赖预定义专家知识、需要针对新工具或任务反复更新模型的现有遥感智能体方案，SkillEarth 显著降低了持续适配动态地球环境的维护成本。
SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution
Recently developed remote sensing (RS) agents execute real-world tasks with complex workflows through multi-step tool invocation. These agents, however, typically rely on predefined expertise or parameter updates. They thus require updating expert knowledge or retraining models whenever new tools, tasks, or execution patterns emerge, limiting their continual adaptability in dynamic Earth environments. In this work, we seek to equip general-purpose agents with RS tool-call knowledge that can be automatically extracted from demonstrated trajectories without expert intervention or parameter updates. Specifically, we propose SkillEarth, a self-evolving skill extraction method that externalizes RS tool-call knowledge as reusable, retrievable, and evolvable skill files and refines them through observation-grounded evolution. Unlike existing automatic skill extraction methods that rely on outcome-based reflection to refine skills holistically, SkillEarth grounds skill evolution in real tool-chain execution and combines dual-judge feedback with a grounded observation routing graph for precise component-level refinement. The resulting skills are generalizable, reliable, and transferable: they improve overall RS tool-call performance across three frontier LLMs and four open-source LLMs, are refined through real tool execution feedback, and support cross-model reuse without retraining. Experiments on OpenEarth-Bench and Earth-Bench demonstrate that SkillEarth achieves better tool selection, argument correctness, execution-order consistency, and task completion than existing RS agents and skill extraction methods.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」「各国 AI 监管法案、合规治理与主权算力政策」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：SkillEarth、智能体、遥感、技能抽取，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Haojun Tang, Wenda Zhao, Xiang Zhou, Qiwei Lin, Lida Huang, Yan Wang），经 AITOP 多维评分管线结构化提炼。