GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support

TL;DR

The paper introduces the GCA framework, combining a GCC-specific climate dataset and a tool-augmented agent to enhance climate decision support and benchmark language models in the region.

Contribution

It presents a novel multimodal dataset and an agentic pipeline tailored for GCC climate analysis, improving model reliability through domain fine-tuning and tool integration.

Findings

Domain fine-tuning and tool use improve LLM reliability.

GCA-DS contains 200k question-answer pairs on GCC climate issues.

The GCA agent produces interpretable visualizations and indices.

Abstract

Climate decision-making in the GCC states increasingly demands systems that can translate heterogeneous scientific and policy evidence into actionable guidance, yet general-purpose large language models (LLMs) remain weak both in region-specific climate knowledge and grounded interaction with geospatial and forecasting tools. We present the GCA framework, which unifies (i) GCA-DS, a curated multimodal dataset grounded in the GCC states, and (ii) Gulf Climate Agent (GCA), a tool-augmented agent for climate analysis. GCA-DS comprises 200k question--answer pairs spanning governmental policies and adaptation plans, NGO and international frameworks, academic literature, and event-driven reporting on heatwaves, dust storms, and floods, complemented with remote-sensing inputs that couple imagery with textual evidence. Building on this foundation, the GCA agent orchestrates a modular tool pipeline grounded in real-time and historical signals and geospatial processing that produces derived indices and interpretable visualizations. Finally, we benchmark open and proprietary LLMs on climate tasks in the GCC states and show that domain fine-tuning and tool integration substantially improve reliability over general-purpose baselines.