TritonDFT: Automating DFT with a Multi-Agent Framework
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.
Cite
@article{arxiv.2603.03372,
title = {TritonDFT: Automating DFT with a Multi-Agent Framework},
author = {Zhengding Hu and Kuntal Talit and Zhen Wang and Haseeb Ahmad and Yichen Lin and Prabhleen Kaur and Christopher Lane and Elizabeth A. Peterson and Zhiting Hu and Elizabeth A. Nowadnick and Yufei Ding},
journal= {arXiv preprint arXiv:2603.03372},
year = {2026}
}