Skill-Based Autonomous Agents for Material Creep Database Construction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yue, Su, Tianhao, Hu, Shunbo, Pan, Deng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917244352593920
author Wu, Yue
Su, Tianhao
Hu, Shunbo
Pan, Deng
author_facet Wu, Yue
Su, Tianhao
Hu, Shunbo
Pan, Deng
contents The advancement of data-driven materials science is currently constrained by a fundamental bottleneck: the vast majority of historical experimental data remains locked within the unstructured text and rasterized figures of legacy scientific literature. Manual curation of this knowledge is prohibitively labor-intensive and prone to human error. To address this challenge, we introduce an autonomous, agent-based framework powered by Large Language Models (LLMs) designed to excavate high-fidelity datasets from scientific PDFs without human intervention. By deploying a modular "skill-based" architecture, the agent orchestrates complex cognitive tasks - including semantic filtering, multi-modal information extraction, and physics-informed validation. We demonstrate the efficacy of this framework by constructing a physically self-consistent database for material creep mechanics, a domain characterized by complex graphical trajectories and heterogeneous constitutive models. Applying the pipeline to 243 publications, the agent achieved a verified extraction success rate exceeding 90% for graphical data digitization. Crucially, we introduce a cross-modal verification protocol, demonstrating that the agent can autonomously align visually extracted data points with textually extracted constitutive parameters ($R^2 > 0.99$), ensuring the physical self-consistency of the database. This work not only provides a critical resource for investigating time-dependent deformation across diverse material systems but also establishes a scalable paradigm for autonomous knowledge acquisition, paving the way for the next generation of self-driving laboratories.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03069
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Skill-Based Autonomous Agents for Material Creep Database Construction
Wu, Yue
Su, Tianhao
Hu, Shunbo
Pan, Deng
Databases
The advancement of data-driven materials science is currently constrained by a fundamental bottleneck: the vast majority of historical experimental data remains locked within the unstructured text and rasterized figures of legacy scientific literature. Manual curation of this knowledge is prohibitively labor-intensive and prone to human error. To address this challenge, we introduce an autonomous, agent-based framework powered by Large Language Models (LLMs) designed to excavate high-fidelity datasets from scientific PDFs without human intervention. By deploying a modular "skill-based" architecture, the agent orchestrates complex cognitive tasks - including semantic filtering, multi-modal information extraction, and physics-informed validation. We demonstrate the efficacy of this framework by constructing a physically self-consistent database for material creep mechanics, a domain characterized by complex graphical trajectories and heterogeneous constitutive models. Applying the pipeline to 243 publications, the agent achieved a verified extraction success rate exceeding 90% for graphical data digitization. Crucially, we introduce a cross-modal verification protocol, demonstrating that the agent can autonomously align visually extracted data points with textually extracted constitutive parameters ($R^2 > 0.99$), ensuring the physical self-consistency of the database. This work not only provides a critical resource for investigating time-dependent deformation across diverse material systems but also establishes a scalable paradigm for autonomous knowledge acquisition, paving the way for the next generation of self-driving laboratories.
title Skill-Based Autonomous Agents for Material Creep Database Construction
topic Databases
url https://arxiv.org/abs/2602.03069