El Agente Potente: High-Throughput Agentic Atomistic Simulations
cs.AI, physics.chem-ph
Submitted: 2026-09-13
Updated: 2026-09-13
Comments: 64 pages, 16 figures, and 3 tables, including Supporting Information. Main text: 24 pages, 6 figures, and 1 table
Code: https://github.com/kenko911/User_Cases_El_Agente_Potente
License: http://creativecommons.org/licenses/by/4.0/
The gist: Foundational machine-learning interatomic potentials (MLIPs) are transforming atomistic simulations by achieving near-ab initio accuracy across large chemical spaces at a fraction of the
Terminology
Abstract
Foundational machine-learning interatomic potentials (MLIPs) are transforming atomistic simulations by achieving near-ab initio accuracy across large chemical spaces at a fraction of the computational cost. A central challenge in using these tools for high-throughput property calculations is translating high-level scientific intent into adaptive simulation campaigns without compromising workflow rigour. We introduce El Agente Potente, an agentic system that combines typed execution graphs with a complementary coding mode for MLIPs-driven atomistic simulations. Typed execution graphs provide structured and provenance-aware execution for standardized workflows, with large language models (LLMs) restricted to planning and routing while deterministic Python components perform scientific computation and validation. Complementing this structured execution, a coding agent constructs customized workflows for tasks requiring greater procedural flexibility while invoking existing Potente functions for supported calculations. We demonstrate El Agente Potente across computational materials discovery, molecular energy-landscape exploration, adsorption, and catalytic reaction workflows, together with systematic benchmarks of reproducibility and LLM token cost. These results establish typed execution graphs and code-based workflow construction as complementary mechanisms for agentic scientific computing, combining controlled, auditable execution with the flexibility required for customized atomistic simulations
Sources
- A Fast, Accurate, and Reactive Equivariant Foundation Potential
- DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
- Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
- Crystalyse: a multi-tool agent for materials design
- Materealize: a multi-agent deliberation system for end-to-end material design and synthesis
- Harnessing AtomisticSkills for Agentic Atomistic Research
- El Agente Quntur: A research collaborator agent for quantum chemistry
- El Agente S'olido: A New Age(nt) for Solid State Simulations
- El Agente Estructural: An Artificially Intelligent Molecular Editor
- El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents
- El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation
- Cross Learning between Electronic Structure Theories for Unifying Molecular, Surface, and Inorganic Crystal Foundation Force Fields
- MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
- Orb-v3: atomistic simulation at scale
- Open Materials Generation with Stochastic Interpolants
- A Foundational Potential Energy Surface Dataset for Materials
- The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models
- MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
- Pushing the limits of unconstrained machine-learned interatomic potentials
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection