Performance of AI agents based on reasoning language models on ALD process optimization tasks

TL;DR

This study evaluates reasoning large language models' ability to autonomously optimize atomic layer deposition processes, demonstrating their success and analyzing their reasoning patterns and variability in a simulated environment.

Contribution

It introduces an autonomous agent built on reasoning LLMs for ALD process optimization and analyzes its reasoning process and variability in a simulated setting.

Findings

Reasoning LLM-based agents successfully optimize ALD processes.

Significant run-to-run variability due to non-deterministic responses.

Model's reasoning aligns with ALD principles but can be misled by prior choices.

Abstract

In this work we explore the performance and behavior of reasoning large language models to autonomously optimize atomic layer deposition (ALD) processes. In the ALD process optimization task, an agent built on top of a reasoning LLM has to find optimal dose times for an ALD precursor and a coreactant without any prior knowledge on the process, including whether it is actually self-limited. The agent is meant to interact iteratively with an ALD reactor in a fully unsupervised way. We evaluate this agent using a simple model of an ALD tool that incorporates ALD processes with different self-limited surface reaction pathways as well as a non self-limited component. Our results show that agents based on reasoning models like OpenAI's o3 and GPT5 consistently succeeded at completing this optimization task. However, we observed significant run-to-run variability due to the non deterministic nature of the model's response. In order to understand the logic followed by the reasoning model, the agent uses a two step process in which the model first generates an open response detailing the reasoning process. This response is then transformed into a structured output. An analysis of these reasoning traces showed that the logic of the model was sound and that its reasoning was based on the notions of self-limited process and saturation expected in the case of ALD. However, the agent can sometimes be misled by its own prior choices when exploring the optimization space.