Democratizing AI scientists using ToolUniverse

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gao, Shanghua, Zhu, Richard, Sui, Pengwei, Kong, Zhenglun, Aldogom, Sufian, Huang, Yepeng, Noori, Ayush, Shamji, Reza, Parvataneni, Krishna, Tsiligkaridis, Theodoros, Zitnik, Marinka
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908605594206208
author Gao, Shanghua
Zhu, Richard
Sui, Pengwei
Kong, Zhenglun
Aldogom, Sufian
Huang, Yepeng
Noori, Ayush
Shamji, Reza
Parvataneni, Krishna
Tsiligkaridis, Theodoros
Zitnik, Marinka
author_facet Gao, Shanghua
Zhu, Richard
Sui, Pengwei
Kong, Zhenglun
Aldogom, Sufian
Huang, Yepeng
Noori, Ayush
Shamji, Reza
Parvataneni, Krishna
Tsiligkaridis, Theodoros
Zitnik, Marinka
contents AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In genomics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model across open- and closed-weight models. ToolUniverse standardizes how AI scientists identify and call tools by providing more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, generates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23426
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Democratizing AI scientists using ToolUniverse
Gao, Shanghua
Zhu, Richard
Sui, Pengwei
Kong, Zhenglun
Aldogom, Sufian
Huang, Yepeng
Noori, Ayush
Shamji, Reza
Parvataneni, Krishna
Tsiligkaridis, Theodoros
Zitnik, Marinka
Artificial Intelligence
Machine Learning
AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because they are bespoke, tied to rigid workflows, and lack shared environments that unify tools, data, and analyses into a common ecosystem. In genomics, unified ecosystems have transformed research by enabling interoperability, reuse, and community-driven development; AI scientists require comparable infrastructure. We present ToolUniverse, an ecosystem for building AI scientists from any language or reasoning model across open- and closed-weight models. ToolUniverse standardizes how AI scientists identify and call tools by providing more than 600 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design. It automatically refines tool interfaces for correct use by AI scientists, generates new tools from natural language descriptions, iteratively optimizes tool specifications, and composes tools into agentic workflows. In a case study of hypercholesterolemia, ToolUniverse was used to create an AI scientist to identify a potent analog of a drug with favorable predicted properties. The open-source ToolUniverse is available at https://aiscientist.tools.
title Democratizing AI scientists using ToolUniverse
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.23426