CatMaster: An Agentic Autonomous System for Computational Heterogeneous Catalysis Research

2026-01-20

AI Summary

This work addresses the challenges commonly encountered in computational heterogeneous catalysis—namely, lengthy workflows, sensitivity to setup details, poor reproducibility, and high manual management overhead. We propose an intelligent agent system powered by a large language model (LLM), which, for the first time, integrates LLM agents with multi-fidelity computational tools, including fast surrogate models and high-accuracy density functional theory (DFT). The system automatically constructs and executes complete catalytic research workflows directly from natural language instructions. A structured project memory mechanism ensures persistent, traceable, and restartable records throughout the workflow while enabling flexible extensibility. Evaluated across four increasingly complex tasks—surface energy computation, adsorption site ranking, high-throughput alloy screening, and out-of-toolset extension—the system substantially reduces the burden of manual scripting and documentation, demonstrating strong automation capabilities and broad applicability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Density functional theory (DFT) is widely used to connect atomic structure with catalytic behavior, but computational heterogeneous catalysis studies often require long workflows that are costly, iterative, and sensitive to setup choices. Besides the intrinsic cost and accuracy limits of first-principles calculations, practical workflow issues such as keeping references consistent, preparing many related inputs, recovering from failed runs on computing clusters, and maintaining a complete record of what was done, can slow down projects and make results difficult to reproduce or extend. Here we present CatMaster, a large-language-model (LLM)-driven agent system that turns natural language requests into complete calculation workspaces, including structures, inputs, outputs, logs, and a concise run record. CatMaster maintains a persistent project record of key facts, constraints, and file pointers to support inspection and restartability. It is paired with a multi-fidelity tool library that covers rapid surrogate relaxations and high-fidelity DFT calculations for validation when needed. We demonstrate CatMaster on four demonstrations of increasing complexity: an O2 spin-state check with remote execution, BCC Fe surface energies with a protocol-sensitivity study and CO adsorption site ranking, high-throughput Pt--Ni--Cu alloy screening for hydrogen evolution reaction (HER) descriptors with surrogate-to-DFT validation, and a demonstration beyond the predefined tool set, including equation-of-state fitting for BCC Fe and CO-FeN4-graphene single-atom catalyst geometry preparation. By reducing manual scripting and bookkeeping while keeping the full evidence trail, CatMaster aims to help catalysis researchers focus on modeling choices and chemical interpretation rather than workflow management.

Problem

• heterogeneous catalysis
• density functional theory
• computational workflow
• reproducibility
• high-throughput screening

Innovation

• LLM-driven agent
• computational catalysis
• multi-fidelity workflow
• automated DFT
• reproducible research