paper-with-me

Papers

TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology

2026-03-22 · Feng Liu, Jian Xu, Xin Cui, Xinghao Wang, Zijie Guo, Jiong Wang, S. Mostafa Mousavi, Xinyu Gu, Hao Chen, Ben Fei, Lihua Fang, Fenghua Ling, Zefeng Li, Lei Bai arxiv

Inferring physical mechanisms that govern earthquake sequences from geophysical observations remains a challenging task, particularly across tectonically distinct environments where similar seismic patterns can reflect different underlying processes. Current seismological processing and interpretation rely heavily on experts' choice of parameters and the synthesis of various seismological products, limiting reproducibility and the formation of generalizable knowledge 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 inferences 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. For the 2025 Santorini-Kolumbo volcanic eruption, the system identifies a structurally guided intrusion model, distinguishing episodic migration via fault channels from the continuous propagation expected in homogeneous crustal failure. By providing a generalizable infrastructure for deriving physical insights from seismic phenomena, TRACE advances the field from expert-dependent analysis toward knowledge-guided autonomous discovery in Earth sciences.

📄 PDF Abstract BibTeX arXiv:2603.21152

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

2026-06-29 · Zihan Guo, Zeyi Chen, Zhiyu Chen, Zicai Cui 외 arxiv

Existing autonomous research agents can support parts of the research process, but most systems still treat research as either an isolated assistant task or a closed workflow. Therefore, autonomous science needs a collab…

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

2026-03-25 · Michael Somma, Markus Großpointner, Paul Zabalegui, Eppu Heilimo 외 arxiv

The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class of operational technol…

End-to-end autonomous scientific discovery on a real optical platform

2026-04-29 · Shuxing Yang, Fujia Chen, Rui Zhao, Junyao Wu 외 arxiv

Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (L…

EnvTrace: Simulation-Based Semantic Evaluation of LLM Code via Execution Trace Alignment -- Demonstrated at Synchrotron Beamlines

2025-11-13 · Noah van der Vleuten, Anthony Flores, Shray Mathur, Max Rakitin 외 arxiv

Evaluating large language models (LLMs) for instrument control requires methods that go beyond standard, stateless algorithmic benchmarks, since the behavior of physical systems cannot be fully captured by unit tests alo…

Code Generation

Traceable Multi-Agent System for Knowledge-Based Forecasting

2026-08-04 · Junhyeok Kang, Sangjun Han, Hyeokjun Choe, Soonyoung Lee arxiv

Enterprise forecasting increasingly relies on autonomous agents that interpret documents, search for data, generate code, and revise models. While this autonomy helps build adaptive forecasting pipelines, it also makes i…