LLM Agents for Knowledge Discovery in Atomic Layer Processing
This work addresses knowledge discovery for materials science researchers, but it is incremental as it repurposes existing tools and focuses on a specific domain.
The paper tackles the problem of using LLM agents for knowledge discovery in materials science, specifically in atomic layer processing, by demonstrating that agents can explore and exploit chemical interactions in a reactor simulation with limited probe capabilities, achieving proof of concept through a parlor game and simulation.
Large Language Models (LLMs) have garnered significant attention for several years now. Recently, their use as independently reasoning agents has been proposed. In this work, we test the potential of such agents for knowledge discovery in materials science. We repurpose LangGraph's tool functionality to supply agents with a black box function to interrogate. In contrast to process optimization or performing specific, user-defined tasks, knowledge discovery consists of freely exploring the system, posing and verifying statements about the behavior of this black box, with the sole objective of generating and verifying generalizable statements. We provide proof of concept for this approach through a children's parlor game, demonstrating the role of trial-and-error and persistence in knowledge discovery, and the strong path-dependence of results. We then apply the same strategy to show that LLM agents can explore, discover, and exploit diverse chemical interactions in an advanced Atomic Layer Processing reactor simulation using intentionally limited probe capabilities without explicit instructions.