Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model Framework

2026-02-24

AI Summary

This work addresses the fundamental limitation imposed by scaling relations among reaction intermediates in conventional oxygen reduction reactions, which hinder the rational design of high-performance single-atom catalysts. To overcome this challenge, we propose MAESTRO, a multi-agent large language model framework that integrates role specialization, in-context learning, autonomous reasoning, and self-reflection to establish a closed-loop system for material generation and evaluation. This approach enables the autonomous extraction and optimization of catalytic design principles, successfully circumventing traditional scaling constraints. Using MAESTRO, we discover novel single-atom catalysts with exceptional performance, thereby providing the first demonstration of the efficacy and scientific insightfulness of multi-agent LLMs in the intelligent discovery of electrocatalytic materials.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• 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: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Large language models (LLMs) are becoming increasingly applied beyond natural language processing, demonstrating strong capabilities in complex scientific tasks that traditionally require human expertise. This progress has extended into materials discovery, where LLMs introduce a new paradigm by leveraging reasoning and in-context learning, capabilities absent from conventional machine learning approaches. Here, we present a Multi-Agent-based Electrocatalyst Search Through Reasoning and Optimization (MAESTRO) framework in which multiple LLMs with specialized roles collaboratively discover high-performance single atom catalysts for the oxygen reduction reaction. Within an autonomous design loop, agents iteratively reason, propose modifications, reflect on results and accumulate design history. Through in-context learning enabled by this iterative process, MAESTRO identified design principles not explicitly encoded in the LLMs' background knowledge and successfully discovered catalysts that break conventional scaling relations between reaction intermediates. These results highlight the potential of multi-agent LLM frameworks as a powerful strategy to generate chemical insight and discover promising catalysts.

Problem

• single atom catalysts
• oxygen reduction reaction
• scaling relations
• catalyst discovery
• electrocatalysis

Innovation

• Multi-Agent LLM
• Reasoning-Driven Design
• Single Atom Catalysts
• In-Context Learning
• Oxygen Reduction Reaction