mlsanityData to 7 Oct 2026

TritonDFT: Automating DFT with a Multi-Agent Framework

arXiv 2603.03372 ↗First posted 2 Mar 2026cond-mat.mtrl-sci cs.MAcited by 5

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 31 of its 51 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

31 of 51 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025VASP Agent: An Agentic Framework for Autonomous First-principles Calculations22 Dec
  2. 2025Operationalizing Serendipity: Multi-Agent AI Workflows for Enhanced Materials Characterization with Theory-in-the-Loop7 Aug
  3. 2025DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation18 Jul
  4. 2025Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents23 Jan
  5. 2024HoneyComb: A Flexible LLM-Based Agent System for Materials Science29 Aug
  6. 2024CACTUS: Chemistry Agent Connecting Tool-Usage to Science2 May

Other references · 25

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  2. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  3. 2023Large Language Modelscited by 774
  4. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  5. 2023What can Large Language Models do in chemistry? A comprehensive benchmark on eight taskscited by 179
  6. 2024Fine-Tuned Language Models Generate Stable Inorganic Materials as Textcited by 92
  7. 2024Efficient Evolutionary Search Over Chemical Space with Large Language Modelscited by 59
  8. 2024LLMatDesign: Autonomous Materials Discovery with Large Language Modelscited by 41
  9. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  10. 2024Are LLMs Ready for Real-World Materials Discovery?cited by 40
  11. 2023MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modelingcited by 35
  12. 2025CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolutioncited by 33
13 more
  1. 2024LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillationcited by 32
  2. 2022A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processingcited by 22
  3. 2015AiiDA: Automated Interactive Infrastructure and Database for Computational Sciencecited by 20
  4. 2025Benchmarking Retrieval-Augmented Generation for Chemistrycited by 19
  5. 2024MatExpert: Decomposing Materials Discovery by Mimicking Human Expertscited by 18
  6. 2025MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Sciencecited by 15
  7. 2024Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Modelcited by 14
  8. 2023PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literaturecited by 13
  9. 2023Reconstructing Materials Tetrahedron: Challenges in Materials Information Extractioncited by 8
  10. 2024MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Designcited by 8
  11. 2025MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledgecited by 3
  12. 2024LABIIUM: AI-Enhanced Zero-configuration Measurement Automation Systemcited by 2
  13. 2025Adaptive AI decision interface for autonomous electronic material discoverycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypothesescited by 1
  2. 2026Harnessing agent memory to build lifelong AI partners for materials scientistscited by 0
  3. 2026Science Done on a Machine by a Machine: AI Agents in Computational Chemistrycited by 0
  4. 2026PrimeScientist: Strategic Allocation of Research Effort in Autonomous Researchcited by 0
  5. 2026CompMat-Bench: Benchmarking AI Agents for Computational Materials Sciencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
  2. 2026Evaluating a 4B open-weights local LLM for agentic DFT workflows: a literature reproducibility audit
  3. 2025GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols
  4. 2026Agentic Discovery of Exchange-Correlation Density Functionals
  5. 2026An LLM agent for end-to-end computational materials discovery
  6. 2026Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
  7. 2026From Data to Theory: Autonomous Large Language Model Agents for Materials Science
  8. 2025Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery