ClimateAgents: A Multi-Agent Research Assistant for Social-Climate Dynamics Analysis

Abstract

The complex interaction between social behaviors and climate change requires more than traditional data-driven prediction; it demands interpretable and adaptive analytical frameworks capable of integrating heterogeneous sources of knowledge. This study introduces ClimateAgents, a multi-agent research assistant designed to support social-climate analysis through coordinated AI agents. Rather than focusing solely on predictive modeling, the framework assists researchers in exploring socio-environmental dynamics by integrating multimodal data retrieval, statistical modeling, textual analysis, and automated reasoning. Traditional approaches to climate analysis often address narrowly defined indicators and lack the flexibility to incorporate cross-domain socio-economic knowledge or adapt to evolving research questions. To address these limitations, ClimateAgents employs a set of collaborative, domain-specialized agents that collectively perform key stages of the research workflow, including hypothesis generation, data analysis, evidence retrieval, and structured reporting. The framework supports exploratory analysis and scenario investigation using datasets from sources such as the United Nations and the World Bank. By combining agent-based reasoning with quantitative analysis of socio-economic behavioral dynamics, ClimateAgents enables adaptive and interpretable exploration of relationships between climate indicators, social variables, and environmental outcomes. The results illustrate how multi-agent AI systems can augment analytical reasoning and facilitate interdisciplinary, data-driven investigation of complex socio-environmental systems.

Figures (8)

• Figure 1: The ClimateAgents LLM generating a sequence of "mixed" and "why" questions to probe the causal and correlative relationships among social indicators and carbon emissions.
• Figure 2: A comparative analysis between user-supplied and LLM-generated responses to climate-related prompts, highlighting differences in interpretability and reasoning.
• Figure 3: Multi-agent collaboration for synthesizing climate-related research. The user prompts the system to summarize studies on climate indicators such as carbon emissions. Core agents coordinate task planning, knowledge retrieval, and data synthesis. The planning tool generates a stepwise plan, while computation and retrieval agents extract relevant studies. The resulting table summarizes key features of the retrieved literature, including study impact, sample period, region, and modeling techniques.
• Figure 4: Reasoning framework for examining social and climate indicators linked to carbon emissions. The user initiates the process, and the core LLM agent coordinates classification, feature correlation, model building, pattern analysis, and evaluation. Outputs are synthesized to support interpretation of policy-relevant insights.
• Figure 5: AI Agents-generated response to a user question about variability in clean fuel access and its impact on environmental policy effectiveness. The dialogue illustrates how AI Agents can support reasoning over socio-environmental systems through hypothesis generation and contextual insight.