AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcity

TL;DR

AIMatDesign is a reinforcement learning framework that enhances inverse materials design by incorporating domain knowledge, data augmentation, and automated refinement, leading to more reliable and efficient discovery of novel materials.

Contribution

The paper introduces AIMatDesign, a novel RL-based approach that integrates knowledge-based rewards, data augmentation, and LLM-guided refinement to improve inverse materials design under data scarcity.

Findings

Outperforms traditional ML and RL methods in efficiency and success rates.

Successfully designed Zr-based alloys with properties close to predictions.

Demonstrates reliable trend capture in material property variation.

Abstract

With the growing demand for novel materials, machine learning-driven inverse design methods face significant challenges in reconciling the high-dimensional materials composition space with limited experimental data. Existing approaches suffer from two major limitations: (I) machine learning models often lack reliability in high-dimensional spaces, leading to prediction biases during the design process; (II) these models fail to effectively incorporate domain expert knowledge, limiting their capacity to support knowledge-guided inverse design. To address these challenges, we introduce AIMatDesign, a reinforcement learning framework that addresses these limitations by augmenting experimental data using difference-based algorithms to build a trusted experience pool, accelerating model convergence. To enhance model reliability, an automated refinement strategy guided by large language models (LLMs) dynamically corrects prediction inconsistencies, reinforcing alignment between reward signals and state value functions. Additionally, a knowledge-based reward function leverages expert domain rules to improve stability and efficiency during training. Our experiments demonstrate that AIMatDesign significantly surpasses traditional machine learning and reinforcement learning methods in discovery efficiency, convergence speed, and success rates. Among the numerous candidates proposed by AIMatDesign, experimental synthesis of representative Zr-based alloys yielded a top-performing BMG with 1.7GPa yield strength and 10.2\% elongation, closely matching predictions. Moreover, the framework accurately captured the trend of yield strength variation with composition, demonstrating its reliability and potential for closed-loop materials discovery.