MARSHA: Multi-Agent RAG System for Hazard Adaptation

Yangxinyu Xie, Bowen Jiang, Tanwi Mallick, Joshua Bergerson, John K Hutchison, Duane Rudolph Verner, Jordan Branham, M. Ross Alexander, Robert Ross, Yan Feng, Leslie-Anne Levy, Weijie J Su, Camillo Jose Taylor

Additional Submission Instructions: For the camera-ready version, please include the author names and affiliations, funding disclosures, and acknowledgements.

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: Retrieval-Augmented Generation (RAG), Multi-Agent Systems, Decision Support for Natural Hazards

Abstract: Large language models (LLMs) are a transformational capability at the frontier of artificial intelligence and machine learning that can support decision-makers in addressing pressing societal challenges such as extreme natural hazard events. As generalized models, LLMs often struggle to provide context-specific information, particularly in areas requiring specialized knowledge. In this work, we propose a retrieval-augmented generation (RAG)-based multi-agent LLM system to support analysis and decision-making in the context of natural hazards and extreme weather events. As a proof of concept, we present WildfireGPT, a specialized system focused on wildfire hazards. The architecture employs a user-centered, multi-agent design to deliver tailored risk insights across diverse stakeholder groups. By integrating natural hazard and extreme weather projection data, observational datasets, and scientific literature through an RAG framework, the system ensures both the accuracy and contextual relevance of the information it provides. Evaluation across ten expert-led case studies demonstrates that WildfireGPT significantly outperforms existing LLM-based solutions for decision support.

Submission Number: 233