From Natural Language to Materials Discovery:The Materials Knowledge Navigation Agent

2026-02-11

AI Summary

Traditional materials discovery relies heavily on expert intuition and costly simulations, resulting in low efficiency. This work proposes the first language-driven autonomous agent framework that translates natural language expressions of scientific intent directly into a sequence of computational actions—including database querying, property prediction, crystal structure generation, and thermodynamic stability assessment—while autonomously distilling quantitative thresholds and interpretable chemical design rules. For the first time, this approach enables direct natural language–guided materials exploration, successfully reproducing known superhard materials, identifying a high-Debye-temperature ceramic screening criterion (Θ_D > 800 K), and predicting novel thermodynamically stable Be-rich carbon compounds within the underexplored temperature range of 1500–1700 K.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Accelerating the discovery of high-performance materials remains a central challenge across energy, electronics, and aerospace technologies, where traditional workflows depend heavily on expert intuition and computationally expensive simulations. Here we introduce the Materials Knowledge Navigation Agent (MKNA), a language-driven system that translates natural-language scientific intent into executable actions for database retrieval, property prediction, structure generation, and stability evaluation. Beyond automating tool invocation, MKNA autonomously extracts quantitative thresholds and chemically meaningful design motifs from literature and database evidence, enabling data-grounded hypothesis formation. Applied to the search for high-Debye-temperature ceramics, the agent identifies a literature-supported screening criterion (Theta_D>800 K), rediscovers canonical ultra-stiff materials such as diamond, SiC, SiN, and BeO, and proposes thermodynamically stable, previously unreported Be-C-rich compounds that populate the sparsely explored 1500-1700 K regime. These results demonstrate that MKNA not only finds stable candidates but also reconstructs interpretable design heuristics, establishing a generalizable platform for autonomous, language-guided materials exploration.

Problem

• materials discovery
• high-performance materials
• natural language
• autonomous exploration
• Debye temperature

Innovation

• Materials Knowledge Navigation Agent
• natural language to materials discovery
• autonomous hypothesis generation
• Debye temperature ceramics
• language-guided materials exploration