DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ziqi, Huang, Hongshuo, Zhao, Hancheng, Xu, Changwen, Zhu, Shang, Janssen, Jan, Viswanathan, Venkatasubramanian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908456020082688
author Wang, Ziqi
Huang, Hongshuo
Zhao, Hancheng
Xu, Changwen
Zhu, Shang
Janssen, Jan
Viswanathan, Venkatasubramanian
author_facet Wang, Ziqi
Huang, Hongshuo
Zhao, Hancheng
Xu, Changwen
Zhu, Shang
Janssen, Jan
Viswanathan, Venkatasubramanian
contents Materials discovery relies on high-throughput, high-fidelity simulation techniques such as Density Functional Theory (DFT), which require years of training, extensive parameter fine-tuning and systematic error handling. To address these challenges, we introduce the DFT-based Research Engine for Agentic Materials Screening (DREAMS), a hierarchical, multi-agent framework for DFT simulation that combines a central Large Language Model (LLM) planner agent with domain-specific LLM agents for atomistic structure generation, systematic DFT convergence testing, High-Performance Computing (HPC) scheduling, and error handling. In addition, a shared canvas helps the LLM agents to structure their discussions, preserve context and prevent hallucination. We validate DREAMS capabilities on the Sol27LC lattice-constant benchmark, achieving average errors below 1\% compared to the results of human DFT experts. Furthermore, we apply DREAMS to the long-standing CO/Pt(111) adsorption puzzle, demonstrating its long-term and complex problem-solving capabilities. The framework again reproduces expert-level literature adsorption-energy differences. Finally, DREAMS is employed to quantify functional-driven uncertainties with Bayesian ensemble sampling, confirming the Face Centered Cubic (FCC)-site preference at the Generalized Gradient Approximation (GGA) DFT level. In conclusion, DREAMS approaches L3-level automation - autonomous exploration of a defined design space - and significantly reduces the reliance on human expertise and intervention, offering a scalable path toward democratized, high-throughput, high-fidelity computational materials discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
Wang, Ziqi
Huang, Hongshuo
Zhao, Hancheng
Xu, Changwen
Zhu, Shang
Janssen, Jan
Viswanathan, Venkatasubramanian
Artificial Intelligence
Materials Science
Materials discovery relies on high-throughput, high-fidelity simulation techniques such as Density Functional Theory (DFT), which require years of training, extensive parameter fine-tuning and systematic error handling. To address these challenges, we introduce the DFT-based Research Engine for Agentic Materials Screening (DREAMS), a hierarchical, multi-agent framework for DFT simulation that combines a central Large Language Model (LLM) planner agent with domain-specific LLM agents for atomistic structure generation, systematic DFT convergence testing, High-Performance Computing (HPC) scheduling, and error handling. In addition, a shared canvas helps the LLM agents to structure their discussions, preserve context and prevent hallucination. We validate DREAMS capabilities on the Sol27LC lattice-constant benchmark, achieving average errors below 1\% compared to the results of human DFT experts. Furthermore, we apply DREAMS to the long-standing CO/Pt(111) adsorption puzzle, demonstrating its long-term and complex problem-solving capabilities. The framework again reproduces expert-level literature adsorption-energy differences. Finally, DREAMS is employed to quantify functional-driven uncertainties with Bayesian ensemble sampling, confirming the Face Centered Cubic (FCC)-site preference at the Generalized Gradient Approximation (GGA) DFT level. In conclusion, DREAMS approaches L3-level automation - autonomous exploration of a defined design space - and significantly reduces the reliance on human expertise and intervention, offering a scalable path toward democratized, high-throughput, high-fidelity computational materials discovery.
title DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
topic Artificial Intelligence
Materials Science
url https://arxiv.org/abs/2507.14267