This review synthesises that literature and argues that it has converged on a common architecture with a common limit, and surveys the open geospatial foundation models that now form the practical substrate for EO modelling, arguing that adaptation strategy rather than architecture is the under-searched design variable.
This paper examines Data Agents from a harness-centric perspective, introducing a taxonomy of Data Agents and associated data environments, and identifying four open reliability problems: inactive semantic calibration, missing clarification, missing experience transfer, and the missing verification-repair repository.
Hua-Chi Zhou, Yu-Jing Zhang, Jia-He Du et al.· 0 citations
The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natural language understanding with tool-based execution. In geographic information systems (GIS), this shift is transforming traditional, expert-driven workflows into semia...
Constantinos Papantoniou, Brian N. Hilton· 0 citations
Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare data, perform domain computations, and derive conclusions from runtime evidence. Existing EO agents typically start from supplied observations, while benchmarks typically pr...
Zhu-Tao Lv, Chen-Hao Dang, Yi-Cong Feng et al.· 0 citations
This work evaluates 25 model and agent systems under a controlled tool-using protocol, then uses controlled studies to locate failures in evidence access, tool selection, memory, reasoning, interaction, and scientific execution.
Zhiqing Cui, Xinxiang Yin, Yihong Tang et al.· 0 citations
GISAgentBench is introduced, a benchmark of 349 multi-step GIS tasks curated from GIS Stack Exchange and instantiated on real public data across six selected geographic areas of interest, enabling strict, deterministic, tolerance-aware output matching beyond LLM judging.
Abhinav Pothuri, Zhe Jiang, Ze-Lin Xu et al.· 0 citations
SeaScope is presented, an explainable AI framework that integrates LLMs, Retrieval-Augmented Generation (RAG), scientific knowledge retrieval, and Google Earth Engine (GEE) to transform natural-language requests into transparent and executable EO workflows.
