2026-10-11T11:02:59Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33965599 2026-09-22T14:37:32Z category_146 category_7 category_8 category_13 category_15 category_734 category_931 category_106 portal_63 item_type_3 month_year_09_2026

ZeoAgent: Autonomous Design of Zeolite Frameworks through Pore-Topology-Guided Generation and Evaluation Jing Ping (1468486) Zhendong Liu (1235259) Space Science Medicine Microbiology Genetics Neuroscience Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy prescribed structural constraints paradigm could address crystalline porous materials representative design tasks design objective within accelerate materials design zeolite structure analysis pore dimensions suited generate valid frameworks evaluation autonomous agents zeolites remains challenging enhanced diffusion performance directed zeolite design periodic pore topology constrained pore topology 4 </ sub existing zeolite frameworks coordinating framework generation autonomous agent system autonomous design framework design zeolite frameworks specific system ai agents pore architectures pore architecture framework candidates yet building work establishes standing challenge rational strategies property prediction property objectives promising approach language objectives jointly reason important class guided generation converts natural computational operations cloud representation Autonomous agents are emerging as a promising approach to assist and accelerate materials design and discovery. For zeolites, an important class of crystalline porous materials, this paradigm could address a long-standing challenge in framework discovery: the lack of rational strategies for coordinating framework generation with property objectives. Yet building such an autonomous agent system for zeolites remains challenging, as performance is governed by periodic pore topology and strict framework connectivity constraints. This requires the agent to jointly reason over pore architectures and generate valid frameworks. Here we present ZeoAgent, a zeolite-specific system that converts natural-language objectives into computational operations for zeolite structure analysis and property prediction as well as framework design. ZeoAgent uses a point-cloud representation of pore architecture to learn from existing zeolite frameworks and guide the generation of framework candidates, which are then evaluated against the design objective within the same loop. We demonstrate ZeoAgent in representative design tasks, including the design of frameworks with prescribed structural constraints, enhanced diffusion performance, and pore dimensions suited for CO₂/CH₄ separation. This work establishes a route for goal-directed zeolite design, showing how AI agents can be adapted to periodic porous materials governed by constrained pore topology. 2026-09-22T00:00:00Z Dataset Dataset 10.1021/acs.jcim.6c02058.s002 https://figshare.com/articles/dataset/ZeoAgent_Autonomous_Design_of_Zeolite_Frameworks_through_Pore-Topology-Guided_Generation_and_Evaluation/33965599 CC BY-NC 4.0