In this section
@article{Li:2026:10.1016/j.seppur.2026.137462,
author = {Li, Y and Zhao, J and Cao, XE and Li, S},
doi = {10.1016/j.seppur.2026.137462},
journal = {Separation and Purification Technology},
title = {A large language model-based multi-agent methodology for intelligent materials screening: A case study on MOFs for CO2 capture},
url = {http://dx.doi.org/10.1016/j.seppur.2026.137462},
volume = {394},
year = {2026}
}
TY - JOUR
AB - Metal-organic frameworks (MOFs) hold significant potential for CO2 capture owing to their tunable structures, large surface areas, and versatile chemistries. However, current screening strategies are often limited to specific application scenarios and overlook the intrinsic properties of materials, thereby limiting the transferability of findings. Here, an intelligent evaluation framework was proposed that leverages large language models (LLMs) to integrate semantic reasoning with numerical performance metrics. The approach combines molecular structure, elemental composition, and synthetic feasibility with molecular simulations and process modeling to optimize the design. Adsorption behavior is obtained from atomistic simulations, while cyclic performance is assessed through equilibrium-based process simulations. Notably, energy utilization efficiency is explicitly incorporated as a central performance indicator and assigned higher weighting, thereby emphasizing practical deployment considerations. These numerical indicators are further combined with semantic scores derived from an LLM-based multi-agent system, enabling a balanced, interpretable ranking of candidate MOFs. This dual-level strategy reconciles rigorous optimization with engineering feasibility, safety, and compliance. By aligning numerical robustness with semantic interpretability, the methodology addresses the scenario-dependence of conventional screening methods and provides a scalable pathway for intelligent material evaluation. Beyond CO2 capture, the framework is readily extensible to diverse adsorption processes and evaluation metrics, highlighting its potential as a next-generation paradigm for material screening and decision support.
AU - Li,Y
AU - Zhao,J
AU - Cao,XE
AU - Li,S
DO - 10.1016/j.seppur.2026.137462
PY - 2026///
SN - 1383-5866
TI - A large language model-based multi-agent methodology for intelligent materials screening: A case study on MOFs for CO2 capture
T2 - Separation and Purification Technology
UR - http://dx.doi.org/10.1016/j.seppur.2026.137462
UR - https://www.sciencedirect.com/science/article/pii/S1383586626007288
VL - 394
ER -
Climate Science
Earth and Life Sciences
Energy and Low-Carbon Futures
Resources and Pollution
Economics and Finance
Health
View all publications and browse by year
Briefing papers and Briefing notes
Grantham Institute Outlooks
Evidence & submission papers
Infographics
Institute reports and analytics notes
Grantham notes
Collaborative publications
Discussion papers
Institute event overviews
Working papers