From Data to Theory: Autonomous Large Language Model Agents for Materials Science
This work addresses the challenge of accelerating scientific modeling and discovery in materials science, though it remains incremental due to limitations in validation and model dependency.
The researchers tackled the problem of automating materials theory development by creating an autonomous LLM agent that can select equation forms, generate code, and test theories against data without human intervention, achieving correct identification of established relationships like the Hall-Petch equation and suggesting new predictive laws such as for strain-dependent HOMO-LUMO gap changes, with performance varying by model (e.g., GPT-5 showed better recovery for specialized equations).
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.