arXiv：cs.AI· Han Luo, Xian Xu, Yinhe Liu, Yanfei Zhong·· 5 小时前
GeoSkill：面向地理空间智能体的经验驱动分层技能学习框架（已撤稿）
GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents
AI 导读
地理空间智能体框架 GeoSkill 已被作者 Han Luo 撤稿，撤稿理由为数值错误。该框架由分层技能库（HSB，含规划技能库与工具技能库）和协作式轨迹驱动技能修订（CTSR）机制组成，在地球空间基准 EarthBench 与 ThinkGeo 上验证了将历史执行经验转化为可复用分层技能的效果。
正文
This paper has been withdrawn by Han Luo
No PDF available, click to view other formats
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.
| Comments: | Withdraw the submission, citing numerical errors |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.13667 [cs.AI] |
| (or arXiv:2609.13667v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.13667 arXiv-issued DOI via DataCite |
Submission history
From: Han Luo [view email]
[v1]
Sat, 12 Sep 2026 02:50:52 UTC (836 KB)
[v2]
Sun, 11 Oct 2026 16:45:12 UTC (1 KB) (withdrawn)
来源：arXiv：cs.AI · arxiv.org