FermiLink is a unified AI agent framework that automates multidomain scientific simulations via separated package knowledge bases and a four-layer progressive disclosure mechanism, reproducing 56% of target figures in benchmarks and generating research-grade results on unpublished problems.
hub
Dreams: Density functional theory based research engine for agentic materials simulation
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
abstract
Materials discovery relies on high-throughput, high-fidelity simulation techniques such as Density Functional Theory (DFT), which require years of training, extensive parameter fine-tuning and systematic error handling. To address these challenges, we introduce the DFT-based Research Engine for Agentic Materials Screening (DREAMS), a hierarchical, multi-agent framework for DFT simulation that combines a central Large Language Model (LLM) planner agent with domain-specific LLM agents for atomistic structure generation, systematic DFT convergence testing, High-Performance Computing (HPC) scheduling, and error handling. In addition, a shared canvas helps the LLM agents to structure their discussions, preserve context and prevent hallucination. We validate DREAMS capabilities on the Sol27LC lattice-constant benchmark, achieving average errors below 1\% compared to the results of human DFT experts. Furthermore, we apply DREAMS to the long-standing CO/Pt(111) adsorption puzzle, demonstrating its long-term and complex problem-solving capabilities. The framework again reproduces expert-level literature adsorption-energy differences. Finally, DREAMS is employed to quantify functional-driven uncertainties with Bayesian ensemble sampling, confirming the Face Centered Cubic (FCC)-site preference at the Generalized Gradient Approximation (GGA) DFT level. In conclusion, DREAMS approaches L3-level automation - autonomous exploration of a defined design space - and significantly reduces the reliance on human expertise and intervention, offering a scalable path toward democratized, high-throughput, high-fidelity computational materials discovery.
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 14roles
background 2representative citing papers
Lang2MLIP is an LLM multi-agent framework that automates end-to-end development of machine learning interatomic potentials from natural language input for heterogeneous materials systems.
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
LLM agents surface methodological critiques of computational-physics papers primarily by re-running calculations, not by reading; a deep case revises a Nature Communications L_G=5 nm claim with attacks missing from 21-reviewer peer review.
AutoDFT presents a closed-loop multi-agent LLM framework achieving 94.1% success on a 34-task DFT benchmark and reliable property predictions on materials databases.
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
LLM syntax accuracy for LAMMPS scripts improved to 91% parser pass rate, yet only 1/80 scripts were scientifically correct on the hardest prompt; an agentic verification skill raised success to 5/6.
QUASAR is a new autonomous LLM-based system that orchestrates multi-scale atomistic simulations and benchmarks as a general reasoning tool rather than a narrow automation script.
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
El Agente Estructural is a new multimodal agent that performs natural-language-driven 3D molecular geometry editing and generation using integrated domain tools and vision-language models.
ChemGraph-XANES is an LLM-based agentic framework that automates FDMNES XANES simulation workflows via schema-constrained tool execution and documentation-grounded parameter selection.
Paimon is an agentic framework that automates atomistic simulations and improves reliability by suppressing silent errors in agent workflows, demonstrated on liquid electrolyte cases and literature reproduction.
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.
RADIANT-LLM is a local-first multi-modal RAG system with provenance tracking that delivers lower hallucination rates than general LLMs on nuclear engineering benchmarks.
citing papers explorer
-
FermiLink: A Unified Agent Framework for Multidomain Autonomous Scientific Simulations
FermiLink is a unified AI agent framework that automates multidomain scientific simulations via separated package knowledge bases and a four-layer progressive disclosure mechanism, reproducing 56% of target figures in benchmarks and generating research-grade results on unpublished problems.
-
Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows
Lang2MLIP is an LLM multi-agent framework that automates end-to-end development of machine learning interatomic potentials from natural language input for heterogeneous materials systems.
-
El Agente Quntur: A research collaborator agent for quantum chemistry
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
-
Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers
LLM agents surface methodological critiques of computational-physics papers primarily by re-running calculations, not by reading; a deep case revises a Nature Communications L_G=5 nm claim with attacks missing from 21-reviewer peer review.
-
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
AutoDFT presents a closed-loop multi-agent LLM framework achieving 94.1% success on a 34-task DFT benchmark and reliable property predictions on materials databases.
-
TSAgent: An Agentic Workflow for Autonomous Transition State Search
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
-
Evaluating LLM-generated code for domain-specific languages: molecular dynamics with LAMMPS
LLM syntax accuracy for LAMMPS scripts improved to 91% parser pass rate, yet only 1/80 scripts were scientifically correct on the hardest prompt; an agentic verification skill raised success to 5/6.
-
QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities
QUASAR is a new autonomous LLM-based system that orchestrates multi-scale atomistic simulations and benchmarks as a general reasoning tool rather than a narrow automation script.
-
Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
-
El Agente Estructural: An Artificially Intelligent Molecular Editor
El Agente Estructural is a new multimodal agent that performs natural-language-driven 3D molecular geometry editing and generation using integrated domain tools and vision-language models.
-
ChemGraph-XANES: An Agentic Framework for XANES Simulation and Curation
ChemGraph-XANES is an LLM-based agentic framework that automates FDMNES XANES simulation workflows via schema-constrained tool execution and documentation-grounded parameter selection.
-
A Robust Agentic Framework for Expert-Level Automation of Atomistic Simulations
Paimon is an agentic framework that automates atomistic simulations and improves reliability by suppressing silent errors in agent workflows, demonstrated on liquid electrolyte cases and literature reproduction.
-
LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.
-
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
RADIANT-LLM is a local-first multi-modal RAG system with provenance tracking that delivers lower hallucination rates than general LLMs on nuclear engineering benchmarks.