HVR-Met: A Hypothesis-Verification-Replaning Agentic System for Extreme Weather Diagnosis

TL;DR

HVR-Met is a multi-agent system that employs a hypothesis-verification-replanning loop to improve extreme weather diagnostics through expert knowledge integration and iterative reasoning.

Contribution

The paper introduces HVR-Met, a novel multi-agent framework with a closed-loop reasoning mechanism for enhanced extreme weather diagnosis.

Findings

System outperforms existing methods in complex diagnostic scenarios

Effective integration of expert knowledge improves reasoning accuracy

New benchmark evaluates atomic-level subtasks in weather diagnostics

Abstract

While deep learning-based weather forecasting paradigms have made significant strides, addressing extreme weather diagnostics remains a formidable challenge. This gap exists primarily because the diagnostic process demands sophisticated multi-step logical reasoning, dynamic tool invocation, and expert-level prior judgment. Although agents possess inherent advantages in task decomposition and autonomous execution, current architectures are still hampered by critical bottlenecks: inadequate expert knowledge integration, a lack of professional-grade iterative reasoning loops, and the absence of fine-grained validation and evaluation systems for complex workflows under extreme conditions. To this end, we propose HVR-Met, a multi-agent meteorological diagnostic system characterized by the deep integration of expert knowledge. Its central innovation is the ``Hypothesis-Verification-Replanning'' closed-loop mechanism, which facilitates sophisticated iterative reasoning for anomalous meteorological signals during extreme weather events. To bridge gaps within existing evaluation frameworks, we further introduce a novel benchmark focused on atomic-level subtasks. Experimental evidence demonstrates that the system excels in complex diagnostic scenarios.