From Data to Theory: Autonomous Large Language Model Agents for Materials Science

TL;DR

This paper introduces an autonomous LLM agent capable of developing, testing, and predicting materials science theories end-to-end, demonstrating success with known equations and proposing new relationships, while highlighting current limitations.

Contribution

The work presents a novel autonomous LLM framework for materials theory development that can generate, test, and refine equations without human input.

Findings

Successfully identified governing equations for well-known relationships.

Demonstrated ability to propose new predictive models.

Showed limitations in validation and potential for incorrect equations.

Abstract

We present an autonomous large language model (LLM) agent for end-to-end, data-driven materials theory development. The model can choose an equation form, generate and run its own code, and test how well the theory matches the data without human intervention. The framework combines step-by-step reasoning with expert-supplied tools, allowing the agent to adjust its approach as needed while keeping a clear record of its decisions. For well-established materials relationships such as the Hall-Petch equation and Paris law, the agent correctly identifies the governing equation and makes reliable predictions on new datasets. For more specialized relationships, such as Kuhn's equation for the HOMO-LUMO gap of conjugated molecules as a function of length, performance depends more strongly on the underlying model, with GPT-5 showing better recovery of the correct equation. Beyond known theories, the agent can also suggest new predictive relationships, illustrated here by a strain-dependent law for changes in the HOMO-LUMO gap. At the same time, the results show that careful validation remains essential, because the agent can still return incorrect, incomplete, or inconsistent equations even when the numerical fit appears strong. Overall, these results highlight both the promise and the current limitations of autonomous LLM agents for AI-assisted scientific modeling and discovery.