HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design

• URL: http://arxiv.org/abs/2609.02746v1
• Date: Wed, 02 Sep 2026 15:48:11 GMT
• Title: HiPoly: a hierarchical polymer-native AI framework for property prediction and generative design
• Abstract summary: HiPoly is a polymer-native AI framework that processes complete polymer descriptions through a three-level hierarchical graph architecture.<n>It encodes inter-monomer connectivity, composition, and molecular weight directly within its architecture.<n>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.
• Score: 2.5787479220592155
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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 papers

• PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design [6.729205331174991]
  We introduce PolyFusionAgent, an interactive framework coupling a multimodal polymer foundation model (PolyFusion) with a tool-augmented, literature-grounded design agent (PolyAgent)<n>PolyFusion aligns complementary polymer views including sequence, topology, 3D geometry, and fingerprints across millions of polymers to learn a shared latent space transferable across chemistries and data regimes.<n>PolyAgent closes the design loop by linking prediction and inverse design with evidence retrieval from the polymer literature, proposing, evaluating, and contextualizing hypotheses with explicit precedent in one workflow.
  arXiv  Detail & Related papers  (2026-05-26T04:45:11Z)
• A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era [57.5440098776759]
  Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with biological behavior.<n>This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models.<n> Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives.
  arXiv  Detail & Related papers  (2026-04-17T15:16:33Z)
• PolyJarvis: LLM Agent for Autonomous Polymer MD Simulations [49.024137619510526]
  We present PolyJarvis, an agent that couples a large language model (LLM) with the RadonPy simulation platform.<n>Given a polymer name or SMILES string, PolyJarvis autonomously executes monomer construction, charge assignment, polymerization, force field parameterization, and property calculation.<n>Results show density predictions within 0.1--4.8% and bulk moduli within 17-24% of reference values for aPS and PMMA.
  arXiv  Detail & Related papers  (2026-04-02T21:43:35Z)
• PolySet: Restoring the Statistical Ensemble Nature of Polymers for Machine Learning [0.0]
  We introduce PolySet, a framework that represents a polymer as a finite, weighted ensemble of chains sampled from an assumed molar-mass distribution.<n>By explicitly acknowledging the statistical nature of polymer matter, PolySet establishes a physically grounded foundation for future polymer machine learning.
  arXiv  Detail & Related papers  (2025-12-15T10:50:48Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• Unifying Polymer Modeling and Design via a Conformation-Centric Generative Foundation Model [29.414571977709098]
  PolyConFM is a polymer foundation model that unifies polymer modeling and design through conformation-centric pretraining.<n>We construct the first high-quality polymer conformation dataset via molecular dynamics simulations to mitigate data sparsity.<n>Experiments demonstrate that PolyConFM consistently outperforms representative task-specific methods on diverse downstream tasks.
  arXiv  Detail & Related papers  (2025-10-15T17:11:44Z)
• polyGen: A Learning Framework for Atomic-level Polymer Structure Generation [4.6516580885528835]
  We introduce polyGen, the first generative model designed specifically for polymer structures from minimal inputs such as repeat unit chemistry alone.<n> polyGen overcomes the limitations of traditional crystal structure prediction methods for polymers, successfully generating realistic and diverse linear and branched conformations.<n>As the first atomic-level proof-of-concept capturing intrinsic polymer flexibility, it marks a new capability in material structure generation.
  arXiv  Detail & Related papers  (2025-04-24T15:26:00Z)
• Inverse Design of Copolymers Including Stoichiometry and Chain Architecture [0.0]
  Machine learning-guided molecular design is a promising approach to accelerate polymer discovery. We develop a novel variational autoencoder architecture encoding a graph and decoding a string. Our model learns a continuous, well organized latent space that enables de-novo generation of copolymer structures.
  arXiv  Detail & Related papers  (2024-09-30T15:37:39Z)
• Compositional Representation of Polymorphic Crystalline Materials [56.80318252233511]
  We introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information.<n>Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation.
  arXiv  Detail & Related papers  (2023-11-17T20:34:28Z)
• A graph representation of molecular ensembles for polymer property prediction [3.032184156362992]
  In contrast to organic molecules, polymers are often not well-defined single structures but an ensemble of similar molecules. We introduce a graph representation of molecular ensembles and an associated graph neural network architecture that is tailored to polymer property prediction.
  arXiv  Detail & Related papers  (2022-05-17T20:31:43Z)
• Learning Neural Generative Dynamics for Molecular Conformation Generation [89.03173504444415]
  We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph. We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
  arXiv  Detail & Related papers  (2021-02-20T03:17:58Z)
• Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders [53.34780987686359]
  Machine learning tools are now commonly employed to virtually screen material candidates with desired properties. This approach is inefficient, and severely constrained by the candidates that human imagination can conceive. We utilize syntax-directed variational autoencoders (VAE) in tandem with Gaussian process regression (GPR) models to discover polymers expected to be robust under three extreme conditions.
  arXiv  Detail & Related papers  (2020-11-04T21:36:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.