Catalyst-Agent: Autonomous heterogeneous catalyst screening and optimization with an LLM Agent

2026-03-01

AI Summary

Traditional catalyst discovery relies heavily on costly experiments or first-principles calculations, resulting in low efficiency. This work proposes Catalyst-Agent—the first autonomous system that deeply integrates large language model (LLM) agents with a materials science toolchain. Built upon the Model Context Protocol architecture, Catalyst-Agent leverages the OPTIMADE API to access materials databases and combines the FAIRchem AdsorbML workflow with the UMA graph neural network to autonomously perform structure modification, adsorption energy prediction, and candidate optimization. Evaluated on oxygen reduction (ORR), nitrogen reduction (NRR), and CO₂ reduction (CO2RR) reactions, the system achieves success rates of 23–34% and typically converges within just one to two iterations, drastically reducing human intervention and advancing catalyst discovery toward an agent-driven paradigm.

Technology Category

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

Application Category

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

Abstract

The discovery of novel catalysts tailored for particular applications is a major challenge for the twenty-first century. Traditional methods for this include time-consuming and expensive experimental trial-and-error approaches in labs based on chemical theory or heavily computational first-principles approaches based on density functional theory. Recent studies show that deep learning models like graph neural networks (GNNs) can significantly speed up the screening and discovery of catalyst materials by many orders of magnitude, with very high accuracy and fidelity. In this work, we introduce Catalyst-Agent, a Model Context Protocol (MCP) server-based, LLM-powered AI agent. It can explore vast material databases using the OPTIMADE API, make structural modifications, calculate adsorption energies using Meta FAIRchem's UMA (GNN) model via FAIRchem's AdsorbML workflow and slab construction, and make useful material suggestions to the researcher in a closed-loop manner, including surface-level modifications to refine near-miss candidates. It is tested on three pivotal reactions: the oxygen reduction reaction (ORR), the nitrogen reduction reaction (NRR), and the CO2 reduction reaction (CO2RR). Catalyst-Agent achieves a success rate of 23-34 percent among all the materials it chooses and evaluates, and manages to converge in 1-2 trials per successful material on average. This work demonstrates the potential of AI agents to exercise their planning capabilities and tool use to operationalize the catalyst screening workflow, provide useful, testable hypotheses, and accelerate future scientific discoveries for humanity with minimal human intervention.

Problem

• heterogeneous catalyst
• catalyst discovery
• catalyst optimization
• ORR
• CO2RR

Innovation

• LLM Agent
• Autonomous Catalyst Discovery
• Graph Neural Networks
• Closed-loop Optimization
• Materials Screening