ToolUniverse: An open platform for democratizing AI scientists

[Submitted on 27 Sep 2025 (v1), last revised 7 Aug 2026 (this version, v3)]

Authors:Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik

View PDF HTML (experimental)

Abstract: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. We present ToolUniverse, an open platform 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 through an AI-tool interaction standard, in which every tool declares its purpose in natural language, a typed schema for its inputs and outputs, and a backend-agnostic invocation format, and applies that standard to more than 2,700 scientific tools and over 130 research skills spanning 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 case studies, ToolUniverse was used to create AI scientists that carried out end-to-end analyses in target assessment, chemical strategy, and clinical-trial safety. The open-source ToolUniverse is available at this https URL.

Submission history

From: Shanghua Gao [view email]
[v1] Sat, 27 Sep 2025 17:38:53 UTC (1,441 KB)
[v2] Wed, 22 Oct 2025 01:03:00 UTC (1,471 KB)
[v3] Fri, 7 Aug 2026 21:29:19 UTC (1,564 KB)