Geospatial agents learn reusable skills from past experiences
GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents
Artificial Intelligence
Summary
Geospatial agents help with mapping and land analysis but need to get better at remembering how they solved past tasks. The authors created GeoSkill, a system that organizes past experiences into reusable skills, making agents smarter at planning and tool use. GeoSkill also uses a team approach to check and fix mistakes in these skills so agents learn more reliably. This makes the agents more accurate and dependable at solving new geospatial problems.
What this means in practice
- •For geospatial data analysts: Enhance automated geographic data analysis by reusing learned task sequences and tool usage patterns to improve accuracy on new projects.
- •For environmental monitoring teams: Improve efficiency and reliability of recurring environmental assessments by applying hierarchical learned skills from past remote sensing tasks.
Authors
Han Luo, Xian Xu, Yinhe Liu, Yanfei Zhong
Abstract
Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings, effective agents must distill prior execution experience into reusable geospatial procedural knowledge to guide future planning and tool use. However, existing memory-augmented paradigms struggle to summarize both long-horizon tool-chain orchestration experience and tool-level invocation constraints in geospatial analysis, while directly relying on LLM self-reflection to update experience often leads to misattribution and unreliable revisions. To address these challenges, we propose GeoSkill, an experience-driven hierarchical skill learning framework for geospatial agents. GeoSkill comprises two core components: (i) a Hierarchical Skill Bank (HSB), consisting of a Planning Skill Bank and a Tool Skill Bank, which respectively distill high-level task-planning experience and tool usage constraints, enabling structured representation and cross-task reuse of historical execution experience; and (ii) a Collaborative Trace-driven Skill Revision (CTSR) mechanism, where Judge, Critic, and Refiner collaboratively perform error identification, skill-level defect localization, and targeted modification, preventing misattributed and unreliable revisions from polluting the skill bank. GeoSkill learns and validates skills from historical executions during development, and freezes the skill bank for retrieval-only guidance on unseen tasks during deployment. Extensive experiments on EarthBench and ThinkGeo demonstrate that GeoSkill effectively transforms historical execution experience into reusable hierarchical skills, improving both end-to-end task accuracy and tool-execution reliability in geospatial tasks.