Adsorb-Agent: Autonomous Identification of Stable Adsorption Configurations via Large Language Model Agent
This addresses the problem of high computational costs in catalyst discovery for researchers, though it appears incremental as it builds on existing LLM methods for a specific bottleneck.
The paper tackles the computationally intensive problem of identifying stable adsorption configurations in catalysis by introducing Adsorb-Agent, an LLM-based agent that strategically explores configurations to reduce initial setups and improve accuracy. It achieves comparable adsorption energies for 84% of cases and lower energies for 35% of cases in tests on twenty diverse systems.
Adsorption energy is a key reactivity descriptor in catalysis. Determining adsorption energy requires evaluating numerous adsorbate-catalyst configurations, making it computationally intensive. Current methods rely on exhaustive sampling, which does not guarantee the identification of the global minimum energy. To address this, we introduce Adsorb-Agent, a Large Language Model (LLM) agent designed to efficiently identify stable adsorption configurations corresponding to the global minimum energy. Adsorb-Agent leverages its built-in knowledge and reasoning to strategically explore configurations, significantly reducing the number of initial setups required while improving energy prediction accuracy. In this study, we also evaluated the performance of different LLMs, including GPT-4o, GPT-4o-mini, Claude-3.7-Sonnet, and DeepSeek-Chat, as the reasoning engine for Adsorb-Agent, with GPT-4o showing the strongest overall performance. Tested on twenty diverse systems, Adsorb-Agent identifies comparable adsorption energies for 84% of cases and achieves lower energies for 35%, particularly excelling in complex systems. It identifies lower energies in 47% of intermetallic systems and 67% of systems with large adsorbates. These findings demonstrate Adsorb-Agent's potential to accelerate catalyst discovery by reducing computational costs and enhancing prediction reliability compared to exhaustive search methods.