Generative retrieval-augmented ontologic graph and multi-agent strategies for interpretive large language model-based materials design

TL;DR

This paper demonstrates how retrieval-augmented ontological graphs and multi-agent strategies enhance large language models' capabilities in materials design, analysis, and interdisciplinary knowledge discovery, with a focus on interpretability and active learning.

Contribution

It introduces a novel retrieval-augmented knowledge graph approach combined with multi-agent strategies to improve LLMs in materials science and interdisciplinary applications.

Findings

Fine-tuning improves domain understanding in LLMs.

Retrieval-augmented graphs enhance interpretability and knowledge recall.

Multi-agent strategies enable complex problem solving and active learning.

Abstract

Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design and manufacturing, including their capacity to work effectively with both human language, symbols, code, and numerical data. Here we explore the use of large language models (LLMs) as a tool that can support engineering analysis of materials, applied to retrieving key information about subject areas, developing research hypotheses, discovery of mechanistic relationships across disparate areas of knowledge, and writing and executing simulation codes for active knowledge generation based on physical ground truths. When used as sets of AI agents with specific features, capabilities, and instructions, LLMs can provide powerful problem solution strategies for applications in analysis and design problems. Our experiments focus on using a fine-tuned model, MechGPT, developed based on training data in the mechanics of materials domain. We first affirm how finetuning endows LLMs with reasonable understanding of domain knowledge. However, when queried outside the context of learned matter, LLMs can have difficulty to recall correct information. We show how this can be addressed using retrieval-augmented Ontological Knowledge Graph strategies that discern how the model understands what concepts are important and how they are related. Illustrated for a use case of relating distinct areas of knowledge - here, music and proteins - such strategies can also provide an interpretable graph structure with rich information at the node, edge and subgraph level. We discuss nonlinear sampling strategies and agent-based modeling applied to complex question answering, code generation and execution in the context of automated force field development from actively learned Density Functional Theory (DFT) modeling, and data analysis.