Agentic Discovery: Closing the Loop with Cooperative Agents

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pauloski, J. Gregory, Chard, Kyle, Foster, Ian T.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915555604168704
author Pauloski, J. Gregory
Chard, Kyle
Foster, Ian T.
author_facet Pauloski, J. Gregory
Chard, Kyle
Foster, Ian T.
contents As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13081
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agentic Discovery: Closing the Loop with Cooperative Agents
Pauloski, J. Gregory
Chard, Kyle
Foster, Ian T.
Multiagent Systems
Artificial Intelligence
As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure.
title Agentic Discovery: Closing the Loop with Cooperative Agents
topic Multiagent Systems
Artificial Intelligence
url https://arxiv.org/abs/2510.13081