PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design

2026-05-26

AI Summary

Polymer discovery is hindered by the vastness of chemical space and fragmented structure–property knowledge, which impede actionable AI-driven design decisions. This work proposes PolyFusion–PolyAgent, an interactive framework that integrates multimodal representation learning with literature-grounded scientific reasoning. PolyFusion enables pretraining and property-conditioned generation within a shared latent space across diverse chemical systems by fusing sequence, topological, 3D geometric, and fingerprint modalities. PolyAgent leverages retrieval-augmented reasoning over scientific literature to generate evidence-based hypotheses. By unifying multimodal alignment with literature-supported inverse design—demonstrated here for the first time—the approach significantly improves thermophysical property prediction accuracy, yields chemically valid and structurally novel polymers, and ensures that the design process remains interpretable, traceable, and verifiable.

Abstract

Polymer discovery is central to fields ranging from energy storage to biomedicine, but it is hindered by an astronomically large chemical design space and fragmented representations of structure, properties, and prior knowledge. This fragmentation leaves many AI models disconnected from physical and experimental reality, restricting their ability to support directly actionable design decisions. Here we introduce PolyFusionAgent, an interactive framework coupling a multimodal polymer foundation model (PolyFusion) with a tool-augmented, literature-grounded design agent (PolyAgent). 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, improving thermophysical property prediction and enabling property-conditioned generation of chemically valid, structurally novel polymers beyond the reference design space. 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. Together, PolyFusionAgent enables interactive, evidence-linked polymer discovery combining large-scale representation learning, multimodal chemical knowledge, and verifiable scientific reasoning.

Problem

• polymer discovery
• chemical design space
• fragmented representations
• property prediction
• inverse design

Innovation

• multimodal foundation model
• polymer inverse design
• shared latent space
• tool-augmented agent
• evidence-based reasoning