Qiangqiang Gu

Zhanghao Zhouyin, Zixi Gan, MingKang Liu et al.

Predicting quantum operator matrices such as Hamiltonian, overlap, and density matrices in the density functional theory (DFT) framework is crucial for material science. Current methods often focus on individual operators and struggle with efficiency and scalability for large systems. Here we introduce a novel deep learning model, SLEM (strictly localized equivariant message-passing) for predicting multiple quantum operators, that achieves state-of-the-art accuracy while dramatically improving computational efficiency. SLEM's key innovation is its strict locality-based design for equivariant representations of quantum tensors while preserving physical symmetries. This enables complex many-body dependency without expanding the effective receptive field, leading to superior data efficiency and transferability. Using an innovative SO(2) convolution and invariant overlap parameterization, SLEM reduces the computational complexity of high-order tensor products and is therefore capable of handling systems requiring the $f$ and $g$ orbitals in their basis sets. We demonstrate SLEM's capabilities across diverse 2D and 3D materials, achieving high accuracy even with limited training data. SLEM's design facilitates efficient parallelization, potentially extending DFT simulations to systems with device-level sizes, opening new possibilities for large-scale quantum simulations and high-throughput materials discovery.

Linfeng Zhang, Siheng Chen, Yuzhu Cai et al.

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale.

Jijie Zou, Zhanghao Zhouyin, Dongying Lin et al.

Quantum transport simulations are essential for understanding and designing nanoelectronic devices, yet the long-standing trade-off between accuracy and computational efficiency has limited their practical applications. We present DeePTB-NEGF, an integrated framework combining deep learning tight-binding Hamiltonian prediction with non-equilibrium Green's Function methodology to enable accurate quantum transport simulations in open boundary conditions with 2-3 orders of magnitude acceleration. We demonstrate DeePTB-NEGF through two challenging applications: comprehensive break junction simulations with over $10^4$ snapshots, showing excellent agreement with experimental conductance histograms; and carbon nanotube field-effect transistors (CNT-FET) at experimental dimensions, reproducing measured transfer characteristics for a 41 nm channel CNT-FET ($\sim 8000$ atoms, $3\times10^4$ orbitals) and predicting zero-bias transmission spectra for a 180 nm CNT ($\sim 3\times 10^4$ atoms, $10^5$ orbitals), showcasing the framework's capability for large-scale device simulations. Our systematic studies across varying geometries confirm the necessity of simulating realistic experimental structures for precise predictions. DeePTB-NEGF bridges the longstanding gap between first-principles accuracy and computational efficiency, providing a scalable tool for high-throughput and large-scale quantum transport simulations that enables previously inaccessible nanoscale device investigations.

Qiangqiang Gu, Shishir Kumar Pandey, Zhanghao Zhouyin

Ab initio based accurate simulation of phonon-assisted optical spectra of semiconductors at finite temperatures remains a formidable challenge, as it requires large supercells for phonon sampling and computationally expensive high-accuracy exchange-correlation (XC) functionals. In this work, we present an efficient approach that combines deep learning tight-binding and potential models to address this challenge with ab initio fidelity. By leveraging molecular dynamics for atomic configuration sampling and deep learning-enabled rapid Hamiltonian evaluation, our approach enables large-scale simulations of temperature-dependent optical properties using advanced XC functionals (HSE, SCAN). Demonstrated on silicon and gallium arsenide across temperature 100-400 K, the method accurately captures phonon-induced bandgap renormalization and indirect/direct absorption processes which are in excellent agreement with experimental findings over five orders of magnitude. This work establishes a pathway for high-throughput investigation of electron-phonon coupled phenomena in complex materials, overcoming traditional computational limitations arising from large supercell used with computationally expensive XC-functionals.