Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent

2024-10-22

arXiv.org

AI Summary

In catalytic material design, accurate prediction of adsorption energies is hindered by the vast configurational space and the computational intractability of identifying global energy minima. To address this, we propose the first large language model (LLM)-based physicochemical reasoning agent framework that embeds domain knowledge into multi-step reasoning planning, enabling knowledge-guided active search for optimal adsorption configurations—thereby transcending conventional enumeration paradigms. Our method establishes an LLM-driven exploration–DFT validation closed loop, drastically reducing computational sampling cost. Evaluated on 20 representative systems, it achieves adsorption energies comparable to reference benchmarks in 83.7% of cases and identifies configurations closer to the true global minimum in 35%. For challenging systems—including intermetallic surfaces and large-molecule adsorption—the success rates reach 46.7% and 66.7%, respectively—demonstrating robust global optimization capability on high-dimensional, non-convex potential energy surfaces.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Metareasoning and Metaheuristics
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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

Abstract

Adsorption energy is a key reactivity descriptor in catalysis, enabling efficient screening for optimal catalysts. However, determining adsorption energy typically requires evaluating numerous adsorbate-catalyst configurations. Current algorithmic approaches rely on exhaustive enumeration of adsorption sites and configurations, which makes the process computationally intensive and does not inherently guarantee the identification of the global minimum energy. In this work, we introduce Adsorb-Agent, a Large Language Model (LLM) agent designed to efficiently identify system-specific stable adsorption configurations corresponding to the global minimum adsorption energy. Adsorb-Agent leverages its built-in knowledge and emergent reasoning capabilities to strategically explore adsorption configurations likely to hold adsorption energy. By reducing the reliance on exhaustive sampling, it significantly decreases the number of initial configurations required while improving the accuracy of adsorption energy predictions. We evaluate Adsorb-Agent's performance across twenty representative systems encompassing a range of complexities. The Adsorb-Agent successfully identifies comparable adsorption energies for 83.7% of the systems and achieves lower energies, closer to the actual global minimum, for 35% of the systems, while requiring significantly fewer initial configurations than conventional methods. Its capability is particularly evident in complex systems, where it identifies lower adsorption energies for 46.7% of systems involving intermetallic surfaces and 66.7% of systems with large adsorbate molecules. These results demonstrate the potential of Adsorb-Agent to accelerate catalyst discovery by reducing computational costs and improving the reliability of adsorption energy predictions.

Problem

• Autonomous identification of stable adsorption configurations
• Reducing computational cost in catalyst discovery
• Improving accuracy of adsorption energy predictions

Innovation

• LLM agent identifies stable adsorption configurations
• Reduces initial configurations via strategic exploration
• Improves accuracy with fewer computational resources