The field of climate science and geospatial analysis is moving towards increased automation and the use of multi-agent systems to improve the efficiency and accuracy of data analysis and decision support. This shift is driven by the need to process large, heterogeneous datasets and to provide reliable and scalable solutions for risk analysis and decision making. Recent developments have focused on the use of large language models and agent-based systems to automate workflows, generate code, and provide context-aware visualizations. These advancements have the potential to substantially advance the field by enabling faster and more accurate analysis of complex climate and geospatial data. Notable papers in this area include:

• ClimateAgent, which presents a multi-agent framework for orchestrating end-to-end climate data analytic workflows, achieving 100% task completion and outperforming baseline approaches.
• Context-Aware Visual Prompting, which introduces a generative AI framework for automating the creation of interactive geospatial dashboards, demonstrating improved performance over baseline approaches.
• Reasoning With a Star, which provides a heliophysics dataset and benchmark for agentic scientific reasoning, addressing the challenges of incorporating physical assumptions and maintaining consistent units.
• EWE, which presents an agentic framework for extreme weather analysis, emulating expert workflows and offering the potential to democratize expertise and intellectual resources.