开源地理分析代理系统，让大模型直接完成复杂多步空间分析任务。
GISclaw: A Comprehensive Open-Source LLM Agent System for Realistic Multi-Step Geospatial Analysis
- 用大模型+沙盒环境实现端到端地理分析，无需商业软件依赖。
- 在50个专家任务上平均成功率97%，最高达100%。
- 适合需要离线部署或高精度空间计算的研究者与工程师。
大多数基于大模型的地理信息系统助手仅能解决与专有平台（如ArcGIS或QGIS）紧密耦合的单一任务，难以应对专业级多步骤、跨格式的分析流程。本文提出GISclaw，一个全面开源的代理系统，可端到端执行真实地理空间分析——包括空间连接、栅格代数、克里金插值、机器学习分类、网络分析和等值区域制图，全部通过Python实现且无商业GIS依赖。GISclaw结合大模型推理核心与预加载开源地理空间栈的持久化Python沙盒，采用三项定制提示规则（模式分析、包约束、领域知识注入）及错误记忆模块实现自我修正。单一后端无关架构支持云端API与本地部署的开源权重大模型，保障离线运行不降性能。在GeoAnalystBench基准测试中，50个专家标注的多步骤任务平均5.8个分析步骤，GISclaw达到最高100%任务成功率与97%平均成功率（三次独立运行）。我们进一步开展1,800次受控实验（50任务×6后端×2架构×3重复），使用自举95%置信区间、配对威尔科克斯检验及综合评分敏感性分析（肯德尔等级相关系数中位数=0.94），并引入三层评估协议：代码结构、推理过程与特定类型输出验证。单代理ReAct循环在所有云后端上均优于双代理规划-执行-重规划流水线（克利夫斯delta=0.15–0.41）；仅本地部署的140亿参数模型从多代理协调中获益，表明架构复杂度应匹配模型能力而非默认增加。
原文摘要 · Abstract (English)
Most LLM-driven GIS assistants solve narrow single-step tasks tightly coupled to proprietary platforms such as ArcGIS or QGIS, limiting their use for the multi-step, cross-format pipelines that define professional geospatial analysis. We present GISclaw, a comprehensive open-source agent system that performs realistic GIS analysis end to end - spatial joins, raster algebra, kriging interpolation, machine-learning classification, network analysis, choropleth cartography - directly through Python with no commercial GIS dependency. GISclaw couples an LLM reasoning core with a persistent Python sandbox pre-loaded with the open-source geospatial stack, three engineered prompt rules (Schema Analysis, Package Constraint, Domain Knowledge Injection), and an Error-Memory module for self-correction. A single backend-agnostic architecture supports both cloud-API and locally deployed open-weight LLM backends, enabling air-gapped deployment without loss of capability. On GeoAnalystBench - 50 expert-curated multi-step tasks averaging 5.8 analytical steps across vector, raster, and tabular data - GISclaw reaches up to 100% task success and 97% mean success over three independent runs. We further conduct 1,800 controlled experiments (50 tasks x 6 backends x 2 architectures x 3 repeats) with bootstrap 95% CIs, paired Wilcoxon tests, and a composite-score sensitivity analysis (Kendall's tau median = 0.94), and introduce a three-layer evaluation protocol combining code structure, reasoning process, and type-specific output verification. The Single-Agent ReAct loop reliably outperforms the Dual-Agent Plan-Execute-Replan pipeline on every cloud backend (Cliff's delta = 0.15-0.41); only the locally deployed 14B model gains from multi-agent orchestration, suggesting architectural complexity should match model capability rather than be added by default.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。