An Agentic Framework for Autonomous Materials Computation

TL;DR

This paper introduces a specialized agentic framework that leverages domain expertise and LLMs to automate complex materials computations reliably, outperforming standalone LLMs in accuracy and robustness.

Contribution

It presents a novel domain-specific agent that ensures physically coherent workflows and reliable automation in first-principles materials computations.

Findings

Significantly outperforms standalone LLMs in accuracy.

Demonstrates robustness across diverse computational tasks.

Establishes a foundation for autonomous scientific experimentation.

Abstract

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific workflows. Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations. By embedding domain expertise, the agent ensures physically coherent multi-step workflows and consistently selects convergent, well-posed parameters, thereby enabling reliable end-to-end computational execution. A new benchmark of diverse computational tasks demonstrates that our system significantly outperforms standalone LLMs in both accuracy and robustness. This work establishes a verifiable foundation for autonomous computational experimentation and represents a key step toward fully automated scientific discovery.