TritonDFT: Automating DFT with a Multi-Agent Framework

TL;DR

TritonDFT is a multi-agent framework designed to automate and optimize the complex workflow of Density Functional Theory calculations, improving accuracy, efficiency, and adaptability in materials science research.

Contribution

It introduces a comprehensive multi-agent system with Pareto-aware parameter inference and a new benchmark for evaluating DFT automation tools.

Findings

Effective full workflow automation for DFT tasks

Enhanced accuracy and cost-efficiency in DFT computations

Open-source tools and benchmark suite available for community use

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.