HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
Abstract
Polymeric materials are central to modern technologies, with applications ranging from energy to health and transportation. Although AI has made significant advances in materials discovery, the hierarchical structure of polymers across multiple length scales makes them inherently difficult to represent in a unified and physically meaningful way. Here we introduce HiPoly, a polymer-native AI framework that processes complete polymer descriptions through a three-level hierarchical graph architecture built on the G2RINS representation. HiPoly encodes stochastic inter-monomer connectivity, composition, and molecular weight directly within its architecture, using physically motivated design principles that mirror the multi-scale nature of polymeric systems. The framework establishes an end-to-end AI-driven workflow from experimental formulation data to property prediction, generative molecular design, and physics-based validation through molecular simulations, all unified by a single polymer representation. We demonstrate state-of-the-art prediction accuracy for thermophysical properties of multi-component polymer systems, with ablation studies confirming that each hierarchical design choice contributes independently to model performance. As an example, the generative design pathway is applied here to the discovery of sustainable alternatives to persistent fluorinated polymers, where it is possible to identify and independently validate PFAS-free candidates with target surface-energy properties. This work demonstrates how polymer-native AI can accelerate discovery by linking representation, prediction, and design across complex polymer chemistries.
Related
- PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation
- PolyBench: A Reproducible Open Benchmark Platform for Repeat-Unit-Based Polymer Property Prediction
- Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction
- Polymer Property Prediction via an Automated Molecular Dynamics Pipeline and Transfer Learning
- Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
BibTeX
@misc{sun2026hipoly,
title = {{HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design}},
author = {Ge Sun and Gervasio Zaldivar and Yuan Tian and Gustavo Perez Lemus and Juhae Park and Daryna Safarian and Ming Han and Juan J. de Pablo},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.02746},
eprint = {2609.02746},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.02746},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
AU - Ge Sun
AU - Gervasio Zaldivar
AU - Yuan Tian
AU - Gustavo Perez Lemus
AU - Juhae Park
AU - Daryna Safarian
AU - Ming Han
AU - Juan J. de Pablo
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2609.02746
UR - https://arxiv.org/abs/2609.02746
AB - Polymeric materials are central to modern technologies, with applications ranging from energy to health and transportation. Although AI has made significant advances in materials discovery, the hierarchical structure of polymers across multiple length scales makes them inherently difficult to represent in a unified and physically meaningful way. Here we introduce HiPoly, a polymer-native AI framework that processes complete polymer descriptions through a three-level hierarchical graph architecture built on the G2RINS representation. HiPoly encodes stochastic inter-monomer connectivity, composition, and molecular weight directly within its architecture, using physically motivated design principles that mirror the multi-scale nature of polymeric systems. The framework establishes an end-to-end AI-driven workflow from experimental formulation data to property prediction, generative molecular design, and physics-based validation through molecular simulations, all unified by a single polymer representation. We demonstrate state-of-the-art prediction accuracy for thermophysical properties of multi-component polymer systems, with ablation studies confirming that each hierarchical design choice contributes independently to model performance. As an example, the generative design pathway is applied here to the discovery of sustainable alternatives to persistent fluorinated polymers, where it is possible to identify and independently validate PFAS-free candidates with target surface-energy properties. This work demonstrates how polymer-native AI can accelerate discovery by linking representation, prediction, and design across complex polymer chemistries.
ER -