TritonDFT: Automating DFT with a Multi-Agent Framework

2026-03-02

AI Summary

This work addresses the challenges in density functional theory (DFT) workflows—namely, their complexity and the difficulty of existing tools in simultaneously achieving automation, task generalization, and an optimal trade-off between accuracy and computational cost. We propose the first end-to-end automated DFT multi-agent system, integrating expert-designed extensible workflows, Pareto-optimal parameter inference, multi-source knowledge fusion, and high-performance computing (HPC) coordination mechanisms. Our contributions include a multi-task-adaptive multi-agent framework, a comprehensive evaluation benchmark named DFTBench, and open-sourced code with a user interface. Experimental results demonstrate that the proposed system significantly outperforms current approaches in scientific accuracy, computational efficiency, and HPC compatibility.

Technology Category

• Multiagent Systems: Distributed Problem Solving
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Density Functional Theory
• workflow automation
• accuracy-cost trade-off
• task adaptation
• multi-step workflow

Innovation

• multi-agent framework
• Density Functional Theory (DFT)
• Pareto-aware optimization
• workflow automation
• DFTBench