Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TritonDFT: Automating DFT with a Multi-Agent Framework

Zhengding Hu, Kuntal Talit, Zhen Wang, Haseeb Ahmad, Yichen Lin, Prabhleen Kaur, Christopher Lane, Elizabeth A. Peterson, Zhiting Hu, Elizabeth A. Nowadnick, Yufei Ding

TL;DR

TritonDFT is presented, a multi-agent framework that enables efficient and accurate DFT execution through an expert-curated, extensible workflow design, Pareto-aware parameter inference, and multi-source knowledge augmentation.

Abstract

Density Functional Theory (DFT) is a cornerstone of materials science, yet executing DFT in practice requires coordinating a complex, multi-step workflow. Existing tools and LLM-based solutions automate parts of the steps, but lack support for full workflow automation, diverse task adaptation, and accuracy-cost trade-off optimization in DFT configuration. To this end, we present TritonDFT, a multi-agent framework that enables efficient and accurate DFT execution through an expert-curated, extensible workflow design, Pareto-aware parameter inference, and multi-source knowledge augmentation. We further introduce DFTBench, a benchmark for evaluating the agent's multi-dimensional capabilities, spanning science expertise, trade0off optimization, HPC knowledge, and cost efficiency. TritonDFT provides an open user interface for real-world usage. Our website is at https://www.tritondft.com. Our source code and benchmark suite are available at https://github.com/Leo9660/TritonDFT.git.

TritonDFT: Automating DFT with a Multi-Agent Framework

TL;DR

TritonDFT is presented, a multi-agent framework that enables efficient and accurate DFT execution through an expert-curated, extensible workflow design, Pareto-aware parameter inference, and multi-source knowledge augmentation.

Abstract

Density Functional Theory (DFT) is a cornerstone of materials science, yet executing DFT in practice requires coordinating a complex, multi-step workflow. Existing tools and LLM-based solutions automate parts of the steps, but lack support for full workflow automation, diverse task adaptation, and accuracy-cost trade-off optimization in DFT configuration. To this end, we present TritonDFT, a multi-agent framework that enables efficient and accurate DFT execution through an expert-curated, extensible workflow design, Pareto-aware parameter inference, and multi-source knowledge augmentation. We further introduce DFTBench, a benchmark for evaluating the agent's multi-dimensional capabilities, spanning science expertise, trade0off optimization, HPC knowledge, and cost efficiency. TritonDFT provides an open user interface for real-world usage. Our website is at https://www.tritondft.com. Our source code and benchmark suite are available at https://github.com/Leo9660/TritonDFT.git.
Paper Structure (27 sections, 3 equations, 7 figures, 5 tables)

This paper contains 27 sections, 3 equations, 7 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. DFT Execution and Challenges
  4. LLM Agents for Automated Material Discovery
  5. TritonDFT: Method and Implementation
  6. Agentic Workflow for Automation
  7. Domain Knowledge Augmentation
  8. User Interface and Interaction
  9. DFTBench: Benchmarking DFT Accuracy and Efficiency with LLM Agents
  10. Evaluation
  11. Experimental Setup
  12. Accuracy and Trade-off Analysis
  13. Time and Cost Efficiency Analysis
  14. Case Study
  15. Conclusion
  16. ...and 12 more sections

Figures (7)

  • Figure 1: DFT execution is a complex, multi-step process requiring heterogeneous domain expertise. Based on an internal survey conducted with 19 domain researchers at the PhD level or above, manually handling each step typically takes minutes to hours. TritonDFT reduces the per-step time to the scale of seconds to minutes, and provides automation across the entire workflow.
  • Figure 2: Energy Deviation and Computational Cost Variations with different DFT Parameters for Silicon (Space Group $Fd\bar{3}m$). Computational cost is normalized as $C/C_0$, where $C$ denotes the actual execution time and $C_0$ corresponds to the execution time with K=6 and ecut=40.
  • Figure 3: The overview of TritonDFT framework.
  • Figure 4: Performance Analysis with Pass Rate and Cost Efficiency across different material types. Cost Efficiency is measured (1 / Cost Factor), averaged over all passed cases within each type.
  • Figure 5: Comparison of TritonDFT's workflow throughput with different LLMs across different DFT tasks.
  • ...and 2 more figures