ALKEMIE Agent: an autonomous platform for computational materials design

2026-08-16

AI Summary

This study addresses the fragmentation and manual dependency inherent in computational materials science workflows by proposing an autonomous agent framework that integrates knowledge, skills, and provenance. Leveraging retrieval-augmented generation, traceable control loops, and adaptive optimization mechanisms, the system enables fully automated execution across the entire materials design pipeline. The platform successfully performs complex tasks, including materials recommendation, phonon calculations, interatomic potential training, and active learning screening. By effectively resolving the disconnection of traditional processes, this work significantly enhances both the intelligence and efficiency of computational materials research. Ultimately, it establishes a novel paradigm for autonomous, data-driven discovery in materials science, streamlining research cycles and reducing human intervention in high-throughput computational workflows.

Abstract

Despite the powerful multi-scale modeling methods and high-throughput infrastructures established in the materials community, real material computation workflows remain fragmented and heavily manual, requiring researchers to constantly bridge software tools, data analysis, and intermediate decisions. This growing gap between methodological capability and practical execution highlights the need for a new kind of autonomous computational framework, one that can coordinate tools, knowledge, and workflows in a more unified and adaptive way. Here, we introduce ALKEMIE Agent, an agentic platform in which retrieval-augmented generation, a materials-computation knowledge base, registered skills, database-supported provenance, AI-assisted structure modeling, bounded task execution, tool-calling iteration, and error-diagnostic assistance are integrated within a traceable control loop. The capabilities of ALKEMIE Agent are demonstrated through applications including materials recommendation, structure modeling, phonon calculations, machine-learned interatomic potential training, LAMMPS simulations, Ab Initio Monte Carlo (AIMC) sampling, and active-learning-based materials screening. Finally, we outline the future directions and challenges for the development of agentic platforms for computational materials design.

Problem

• computational materials design
• autonomous platform
• fragmented workflows
• manual intervention

Innovation

• Autonomous Agent
• Retrieval-Augmented Generation
• Computational Materials Design
• Traceable Control Loop
• Workflow Automation