Empowering Scientific Workflows with Federated Agents

TL;DR

This paper introduces Academy, a middleware enabling the deployment and management of autonomous, stateful agents across diverse scientific cyberinfrastructure to facilitate complex, scalable research workflows.

Contribution

It presents a novel middleware platform, Academy, designed for deploying federated agents in scientific environments with support for asynchronous execution and heterogeneous resources.

Findings

Demonstrates high performance and scalability in HPC environments

Supports diverse scientific applications like materials discovery and astronomy

Enables complex agent-based workflows across federated systems

Abstract

Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and target conversational, cloud-native applications (e.g., LLM-based AI chatbots). In contrast, scientific applications require myriad agents be deployed and managed across diverse cyberinfrastructure. Here we introduce Academy, a modular and extensible middleware designed to deploy autonomous agents across the federated research ecosystem, including HPC systems, experimental facilities, and data repositories. To meet the demands of scientific computing, Academy supports asynchronous execution, heterogeneous resources, high-throughput data flows, and dynamic resource availability. It provides abstractions for expressing stateful agents, managing inter-agent coordination, and integrating computation with experimental control. We present microbenchmark results that demonstrate high performance and scalability in HPC environments. To explore the breadth of applications that can be supported by agentic workflow designs, we also present case studies in materials discovery, astronomy, decentralized learning, and information extraction in which agents are deployed across diverse HPC systems.