TRACE: A Multi-Agent System for Autonomous Physical Reasoning in Seismological
This addresses the challenge of expert-dependent, non-reproducible analysis in seismology by enabling autonomous, physically grounded inference across different tectonic environments.
The paper tackles the problem of inferring physical mechanisms from earthquake sequences by introducing TRACE, a multi-agent system that autonomously identifies mechanisms like stress-perturbation-induced delayed triggering in the 2019 Ridgecrest sequence and structurally guided intrusion in the Santorini-Kolumbo case.
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.