Empowering Scientific Workflows with Federated Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kamatar, Alok, Pauloski, J. Gregory, Babuji, Yadu, Chard, Ryan, Sakarvadia, Mansi, Babnigg, Daniel, Chard, Kyle, Foster, Ian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910003881836544
author Kamatar, Alok
Pauloski, J. Gregory
Babuji, Yadu
Chard, Ryan
Sakarvadia, Mansi
Babnigg, Daniel
Chard, Kyle
Foster, Ian
author_facet Kamatar, Alok
Pauloski, J. Gregory
Babuji, Yadu
Chard, Ryan
Sakarvadia, Mansi
Babnigg, Daniel
Chard, Kyle
Foster, Ian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05428
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Empowering Scientific Workflows with Federated Agents
Kamatar, Alok
Pauloski, J. Gregory
Babuji, Yadu
Chard, Ryan
Sakarvadia, Mansi
Babnigg, Daniel
Chard, Kyle
Foster, Ian
Multiagent Systems
Distributed, Parallel, and Cluster Computing
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.
title Empowering Scientific Workflows with Federated Agents
topic Multiagent Systems
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2505.05428