From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
Abstract
The convergence of large language models, materials-specific foundation models, and agentic artificial intelligence is reshaping the paradigm of computational materials discovery. While high-throughput computation, automated workflows, and data-driven modeling have greatly expanded the scale of materials exploration, the core scientific decision-making loop remains largely human-directed. Agentic AI introduces the possibility of systems that can autonomously reason about materials objectives, execute simulations, and refine strategies. However, the rapid emergence of such systems has created a critical need for a unified and operational framework to define, evaluate, and guide scientific autonomy in computational materials discovery. In this Perspective, we propose the Computational Materials Agent Autonomy Level (CMA-AL) framework, a hierarchical taxonomy defining six levels of autonomous agency in computational materials science: scripted excecutor, LLM-assisted operator, adaptive explorer, experiment-ready modeler, agentic digital twin, and self-extending intelligence. We further map emerging agentic systems onto the framework and identify key scientific and technological challenges toward higher autonomy. CMA-AL provides a common language for characterizing agentic computational materials discovery, evaluating the maturity of emerging systems, and guiding their evolution toward increasingly autonomous materials discovery.
Related
- Automated Discovery of Physically Interpretable Subgrid Length Scales for Detached Eddy Simulation via Agentic AI
- False-science induction in autonomous scientific discovery
- Brilliance: toward autonomous computational research in particle accelerator physics
- Autonomous discovery of reaction networks from active-learning-driven reactive molecular dynamics
- Divergent strategies and convergent outcomes in autonomous materials discovery
BibTeX
@misc{zhu2026from,
title = {{From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science}},
author = {Linggang Zhu and Jian Zhou and Zhimei Sun},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36469},
eprint = {2609.36469},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36469},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
AU - Linggang Zhu
AU - Jian Zhou
AU - Zhimei Sun
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.36469
UR - https://arxiv.org/abs/2609.36469
AB - The convergence of large language models, materials-specific foundation models, and agentic artificial intelligence is reshaping the paradigm of computational materials discovery. While high-throughput computation, automated workflows, and data-driven modeling have greatly expanded the scale of materials exploration, the core scientific decision-making loop remains largely human-directed. Agentic AI introduces the possibility of systems that can autonomously reason about materials objectives, execute simulations, and refine strategies. However, the rapid emergence of such systems has created a critical need for a unified and operational framework to define, evaluate, and guide scientific autonomy in computational materials discovery. In this Perspective, we propose the Computational Materials Agent Autonomy Level (CMA-AL) framework, a hierarchical taxonomy defining six levels of autonomous agency in computational materials science: scripted excecutor, LLM-assisted operator, adaptive explorer, experiment-ready modeler, agentic digital twin, and self-extending intelligence. We further map emerging agentic systems onto the framework and identify key scientific and technological challenges toward higher autonomy. CMA-AL provides a common language for characterizing agentic computational materials discovery, evaluating the maturity of emerging systems, and guiding their evolution toward increasingly autonomous materials discovery.
ER -