TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological Science

2026-03-22

AI Summary

This study addresses the limitations of traditional earthquake interpretation, which relies heavily on expert experience and struggles to ensure reproducibility and cross-regional transferability in tectonically diverse settings with complex seismic source mechanisms. The authors propose TRACE, a multi-agent system that integrates the reasoning and planning capabilities of large language models with formal seismological constraints to automatically generate physically consistent, auditable, and mechanistic interpretations directly from raw observational data. This approach enables, for the first time, cross-perspective reasoning and automated holistic evaluation, shifting earthquake interpretation from expert-driven analysis toward knowledge-guided autonomous discovery. Applied to the 2019 Ridgecrest sequence, TRACE identified a stress-perturbation-induced delayed triggering mechanism, and in the Santorini-Kolumbo region, it revealed a tectonically guided magma intrusion pattern—both significantly outperforming conventional homogeneous rupture assumptions.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Intelligent Robots: Multi-Robot Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Inferring the physical mechanisms that govern earthquake sequences from indirect geophysical observations remains difficult, particularly across tectonically distinct environments where similar seismic patterns can reflect different underlying processes. Current interpretations rely heavily on the expert synthesis of catalogs, spatiotemporal statistics, and candidate physical models, limiting reproducibility and the systematic transfer of insight across settings. Here we present TRACE (Trans-perspective Reasoning and Automated Comprehensive Evaluator), a multi-agent system that combines large language model planning with formal seismological constraints to derive auditable, physically grounded mechanistic inference from raw observations. Applied to the 2019 Ridgecrest sequence, TRACE autonomously identifies stress-perturbation-induced delayed triggering, resolving the cascading interaction between the Mw 6.4 and Mw 7.1 mainshocks; in the Santorini-Kolumbo case, the system identifies a structurally guided intrusion model, distinguishing fault-channeled episodic migration from the continuous propagation expected in homogeneous crustal failure. By providing a generalizable logical infrastructure for interpreting heterogeneous seismic phenomena, TRACE advances the field from expert-dependent analysis toward knowledge-guided autonomous discovery in Earth sciences.

Problem

• earthquake sequences
• physical mechanisms
• seismological interpretation
• heterogeneous seismic phenomena
• expert-dependent analysis

Innovation

• multi-agent system
• autonomous physical reasoning
• large language models
• seismological inference
• mechanistic interpretation