LLM-driven discovery for carbon allotropes with bond-network entropy

Abstract

The discovery of novel carbon allotropes with tailored thermal and mechanical properties is critical for advanced thermal management. However, exploring the vast configurational space of carbon using \textit{ab initio} calculations remains computationally prohibitive. Driven by the rich topological landscape of carbon, where the competition between $sp,s{p}^2,$ and $s{p}^3$ hybridization states dictates material performance, we establish a closed-loop AI framework to explore this complex configurational space. We introduce a hybridization entropy descriptor to guide the search beyond conventional forms. Here, we establish a closed-loop AI framework that synergizes a Large Language Model (LLM) for structural generation with a Machine Learning Potential (MLP) for accelerated evaluation. Leveraging CrystaLLM to generate candidates and an iteratively refined MLP for high-fidelity validation, we screened thousands of structures to identify several stable allotropes with exotic properties. Specifically, we report ``yne-diamond C${}_{12}$'' and ``yne-hex-diamond C${}_8$'', which exhibit extreme thermal anisotropy and ultralow in-plane shear stiffness arising from their mixed $sp$-$s{p}^3$ hybridization. Furthermore, we discovered a complex $sp$-$s{p}^2$-$s{p}^3$ hybridized C${}_{12}$ phase that combines metallic conductivity with an anomalous negative Poisson's ratio. Notably, we identified a superhard phase (C16_3) possessing a calculated Vickers hardness (103.3 GPa) exceeding that of diamond 96 GPa). Microscopic analysis reveals that thermal transport in these materials is governed by the interplay between rigid frameworks and flexible linkers. This work expands the known carbon phase space and demonstrates the efficacy of coupling generative AI with machine learning potentials for the accelerated inverse design of functional materials.

References in corpus (17)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Crystal Structure Prediction via Particle Swarm Optimization
• Intrinsic Correlation between Hardness and Elasticity in Polycrystalline Materials and Bulk Metallic Glasses
• Unified theory of thermal transport in crystals and disordered solids
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Novel Two-Dimensional Silicon Dioxide with in-plane Negative Poisson's Ratio
• Monolayer fullerene networks as photocatalysts for overall water splitting
• Spectral Decomposition of Thermal Conductivity: Comparing Velocity Decomposition Methods in Homogeneous Molecular Dynamics Simulations
• Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene
• Deep learning generative model for crystal structure prediction
• The role of high-order anharmonicity and off-diagonal terms in thermal conductivity: a case study of multi-phase CsPbBr3
• Machine learning for predicting ultralow thermal conductivity and high ZT in complex thermoelectric materials
• Monolayer C${}_{60}$ networks: A first-principles perspective
• Copper delocalization leads to ultralow thermal conductivity in chalcohalide CuBiSeCl2
• Bonding Hierarchy and Coordination Interaction Leading to High Thermoelectricity in Wide Bandgap TlAgI2
• PINK: physical-informed machine learning for lattice thermal conductivity
• Anomalous thermal conductivity in 2D silica nanocages of immobilizing noble gas atom