ALKEMIE Agent is introduced, an agentic platform in which retrieval-augmented generation, a materials-computation knowledge base, registered skills, database-supported provenance, AI-assisted structure modeling, bounded task execution, tool-calling iteration, and error-diagnostic assistance are integrated within a traceable control loop.
Abstract
Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computation workflows remain fragmented and heavily manual, requiring researchers to constantly bridge software tools, data analysis, and intermediate decisions. This growing gap between methodological capability and practical execution highlights the need for a new kind of autonomous computational framework, one that can coordinate tools, knowledge, and workflows in a more unified and adaptive way. Here, we introduce ALKEMIE Agent, an agentic platform in which retrieval-augmented generation, a materials-computation knowledge base, registered skills, database-supported provenance, AI-assisted structure modeling, bounded task execution, tool-calling iteration, and error-diagnostic assistance are integrated within a traceable control loop. The capabilities of ALKEMIE Agent are demonstrated through applications including materials recommendation, structure modeling, phonon calculations, machine-learned interatomic potential training, LAMMPS simulations, Ab Initio Monte Carlo (AIMC) sampling, and active-learning-based materials screening. Finally, we outline the future directions and challenges for the development of agentic platforms for computational materials design.
Computational materials modeling connects physical theory, atomistic mechanisms, and materials design, but its value depends on workflows that are specified, executed, checked, and interpreted with scientific rigor. Agents built on large language models are beginning to link materials knowledge with databases, simulation software, workflow controllers, and feedback mechanisms, enabling greater automation of computational research. However, most reported successes remain concentrated in scaffolded settings for density functional theory, molecular dynamics, and related atomistic simulations, where tasks, engines, validators, and target outputs are predefined. This review analyzes computational materials agents across three interconnected dimensions: architecture, executable workflow practices, and evaluation evidence. We examine how current systems translate materials questions into computational tasks, identify the settings in which reliability and recovery have been demonstrated, and explain why runnable calculations should be distinguished from scientifically justified conclusions. By clarifying the evidence required for traceable, reproducible, and reusable workflows, this review aims to guide the development of computational materials agents from task demonstrations to practical scientific tools.
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
T. Ko, Jia-Ru Bai, Thomas Swanick et al.· 0 citations
By connecting the heterogeneous stages of computational materials discovery, the LLM-based agents of MAESTRO can operate across application domains and uncover high-performance materials that conventional screening approaches would be unlikely to consider.
Yun-Tong Chen, Ju Huang, Yu Liu et al.· 0 citations
CheMLFlow is an open-source platform for building and executing end-to-end, high-throughput, and agentic workflows for scientific and technological applications. CheMLFlow targets a common bottleneck in scientific machine learning development, where researchers often need to assemble data acquisition, curation, representation, model training, validation, screening, interpretation, and reporting into a reproducible pipeline, even when their primary research contribution concerns only one stage. CheMLFlow provides modular workflow components, ready-to-run reference pipelines, standardized artifacts, and evaluation outputs that reduce orchestration overhead and support benchmarking across methods and datasets. The platform is designed to be extensible, reproducible, and automation friendly, with pluggable representations and models, deterministic splits, explicit run artifacts, batch execution, and report generation. As scientific software increasingly moves toward agent assisted experimentation, CheMLFlow's configuration driven workflows and structured outputs also provide a practical interface for coding agents to help users construct experiments, inspect results, and summarize findings under human supervision. This article describes the system architecture, core workflows, and benchmarks that reach literature performance for quantum mechanical, physicochemical and bioactivity property prediction, and use cases involving time series datasets demonstrating applications beyond molecular chemistry datasets.
Brendan Smith, S. López-Moreno, E. Dolores-Cuenca et al.· 0 citations
Metal-organic frameworks (MOFs) and covalent organic frameworks (COFs) are highly tunable in pore structure and chemical environment, yet their discovery remains slow and fragmented. Synthesis reports are often difficult to compare, characterization data are laborious to interpret, and computational predictions rarely guide experiments directly. Recent advances in large language models (LLM) have enabled the development of artificial intelligence (AI) agents that can interpret research goals, search the literature and databases, call external tools, and adapt workflows based on intermediate results. In this review, we distinguish three stages of AI-agent development in MOFs and COFs research: LLM-native, human-mediated systems; database-grounded, tool-using agents; and experiment-integrated, feedback-driven platforms. This progression reflects increasing scientific grounding and experimental agency. In our view, further progress will depend less on scaling language models alone than on developing traceable machine-actionable data, chemistry-aware validation, persistent experimental memory, and robust interfaces between AI agents and laboratory automation.
Jia-Yu Yu, Zihao Jiang, Donglin He· AI Agent· 0 citations
Multi-physics simulations are essential for understanding and monitoring intricate subsurface processes such as CO2 storage. Their computational demands call for surrogate models and, for unstructured meshes, Graph Neural Networks (GNNs) are natural candidates. The main bottleneck in developing them is generating and managing the large, physically consistent simulation datasets required for training. To address this challenge, we present Agents4GEOS, an AI-agent framework built on the Model Context Protocol (MCP) that provides 52 domain-aware tools for natural-language-driven workflows with GEOS, an open-source multi-physics simulator. The agent facilitates input-file creation, mesh inspection, fluid-property computation, and result post-processing. Through human-curated skills and fresh-context subagents coordinated by an orchestrator, the system executes complex workflows, evaluates simulation outputs, diagnoses issues, and suggests improvements, grounding every quantity in actual computation. By automating routine tasks, Agents4GEOS allows domain experts to focus on the most challenging aspects of their work.
Adriano M. A. Côrtes, R. M. Velho, F. Rochinha et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
