An LLM agent for end-to-end computational materials discovery
Abstract
Coordinating multi-scale tasks is an effective strategy for computational materials discovery, yet the diverse algorithms and tools involved make this process highly challenging. Here we present DREAMS, a large language model (LLM)-based agent system capable of executing the entire screening pipeline for metal-organic frameworks (MOFs). DREAMS processes a large body of MOF literature, links publications to their crystal structures, and curates them into a computation-ready database, which is then screened with progressively more expensive simulations. The promising candidates identified for separation under wet flue gas conditions all originate from independent studies. By bridging the heterogeneous stages from literature mining to high-throughput simulation, DREAMS operates across application domains and enables even non-experts to discover high-performance materials in an end-to-end, automated manner.
Related
- Organizational Learning in Materials Discovery Campaigns: Which Databases, Calculations, and Agent Teams Pay Off
- From Automated Simulation to Autonomous Discovery: A Hierarchical Framework for Agentic Computational Materials Science
- High-Throughput Computational Discovery of Inverted Resistive Switching in Two-Dimensional Materials
- ORCHID: Connecting Finite-Temperature Thermodynamic Evidence to Computational Materials Discovery
- Agentic programs: an emerging form of scientific software in computational materials science
BibTeX
@misc{yuntong2026agent,
title = {{An LLM agent for end-to-end computational materials discovery}},
author = {Chen Yuntong and Huang Lijiang and Li Yingqi and Liu Yu and Zhao Dan and Sun Mingqi and Ju Chentian and Liu Yanbing and Li Xiao-Yan and Zhao Guobin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.20434},
eprint = {2608.20434},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.20434},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - An LLM agent for end-to-end computational materials discovery
AU - Chen Yuntong
AU - Huang Lijiang
AU - Li Yingqi
AU - Liu Yu
AU - Zhao Dan
AU - Sun Mingqi
AU - Ju Chentian
AU - Liu Yanbing
AU - Li Xiao-Yan
AU - Zhao Guobin
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2608.20434
UR - https://arxiv.org/abs/2608.20434
AB - Coordinating multi-scale tasks is an effective strategy for computational materials discovery, yet the diverse algorithms and tools involved make this process highly challenging. Here we present DREAMS, a large language model (LLM)-based agent system capable of executing the entire screening pipeline for metal-organic frameworks (MOFs). DREAMS processes a large body of MOF literature, links publications to their crystal structures, and curates them into a computation-ready database, which is then screened with progressively more expensive simulations. The promising candidates identified for separation under wet flue gas conditions all originate from independent studies. By bridging the heterogeneous stages from literature mining to high-throughput simulation, DREAMS operates across application domains and enables even non-experts to discover high-performance materials in an end-to-end, automated manner.
ER -