Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery

2026-06-27

AI Summary

This work proposes a scalable, AI-driven framework that integrates modular AI agents into complex scientific workflows to overcome the heavy reliance on expert intervention in traditional microkinetic studies, which hinders efficient autonomous exploration in exascale computing environments. By synergistically combining high-performance computing, scientific surrogate models, and reliability assessment mechanisms, the framework enables automated discovery, validation, and failure recovery of microkinetic parameters. This approach substantially enhances the autonomy, robustness, and scalability of scientific discovery pipelines while significantly reducing manual oversight. The methodology establishes a new paradigm for autonomous materials discovery and holds broad applicability across computational science domains requiring iterative, large-scale parameter optimization and validation.

Abstract

We present a scalable AI-driven framework that advances autonomous scientific discovery by combining agentic workflow automation, high-performance computing, and scientific surrogate models. Using microkinetics discovery as a testbed, the work demonstrates how AI can reduce expert intervention, recover from failed simulations, and systematically evaluate surrogate model reliability. This study shows how AI skills can transform complex domain workflows into robust, scalable capabilities for next-generation materials research.

Problem

• Exascale AI
• Autonomous Discovery
• Microkinetics
• Surrogate Models
• Scientific Workflows

Innovation

• scalable AI
• autonomous discovery
• microkinetics
• surrogate models
• agentic workflow