cond-mat.mtrl-sciNov 19, 2026

Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation

Authors: Zhiwei Li, Yuhao Zhou, Yikai Yang, Haonan Wang, Qing Ye, Jiancheng Lv, Kazunari Matsuda

Organizations: Institute of Advanced Energy, Kyoto University, Uji, Kyoto 611-0011, Japan · DICALab, School of Computing, Sichuan University, China

Abstract

First-principles structural relaxation and band calculations require substantial computation and expertise. Here we present Perfumer, a large language model-based agentic framework that couples Quantum ESPRESSO with two predictive models. Across tested structures, pre-relaxation with Perfumer-relax model followed by QE refinement yielded a 2.75-fold overall speedup over QE alone. Perfumer-band model combines a periodic graph neural network with a latent Hermitian spectral head returns 12 band energies at any requested wavevector, preserving reciprocal lattice periodicity and time-reversal symmetry without constructing Hamiltonian. Trained on 125,153 self-curated band structures, Perfumer-band model reaches a median per-material mean absolute error of 0.157 eV on 2,607 test materials, including lanthanide, actinide and magnetic compounds, from held-out composition families spanning 85 elements, taking about 97 ms per material on two consumer CPU cores. The agent turns natural-language requests into relaxation-to-band workflows, from a single uploaded structure to automatically constructed new candidates and returns predicted properties.

Explore similar work

CardsList
  1. Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop

    Jun 29, 2026Chenmu Zhang, Boris I. YakobsonGraph Neural NetworksLarge Language Model-Guided Optimization

  2. PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science

    Nov 2, 2026Xuwei Liu, Zhimin Zhang, Xiaoguang Hu +5Computational Materials ScienceMaterials Property Prediction

  3. ALKEMIE Agent: an autonomous platform for computational materials design

    Aug 16, 2026Hongfu Huang, Yuzhe Li, Ao Xu +14AI Agents for Scientific DiscoveryComputational Materials Science