# ToolUniverse: An open platform for democratizing AI scientists

arXiv: https://arxiv.org/abs/2509.23426 · HTML: https://mlsanity.com/paper/2509.23426/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 4 of 4)

- [LAB-Bench: Measuring Capabilities of Language Models for Biology Research](https://mlsanity.com/paper/2407.10362/) (2024)
- [Empowering Biomedical Discovery with AI Agents](https://mlsanity.com/paper/2404.02831/) (2024)
- [TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools](https://mlsanity.com/paper/2503.10970/) (2025)
- [Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy](https://mlsanity.com/paper/2402.04247/) (2024)

## Built on by (most cited first, 24 of 24)

- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources](https://mlsanity.com/paper/2604.03964/) (2026)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [Accelerating Scientific Discovery with Autonomous Goal-evolving Agents](https://mlsanity.com/paper/2512.21782/) (2025)
- [PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature](https://mlsanity.com/paper/2510.10909/) (2025)
- [Benchmarking AI Agents for Addressing Scientific Challenges Across Scales](https://mlsanity.com/paper/2606.12736/) (2026)
- [Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics](https://mlsanity.com/paper/2510.09901/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation](https://mlsanity.com/paper/2510.15624/) (2025)
- [Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation](https://mlsanity.com/paper/2606.05241/) (2026)
- [Towards a Medical AI Scientist](https://mlsanity.com/paper/2603.28589/) (2026)
- [Harnessing AtomisticSkills for Agentic Atomistic Research](https://mlsanity.com/paper/2605.24002/) (2026)
- [SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis](https://mlsanity.com/paper/2606.24235/) (2026)
- [MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization](https://mlsanity.com/paper/2512.20135/) (2025)
- [Large Language Models Lack Temporal Awareness of Medical Knowledge](https://mlsanity.com/paper/2605.13045/) (2026)
- [Structural Enforcement of Statistical Rigor in AI-Driven Discovery: A Functional Architecture](https://mlsanity.com/paper/2511.06701/) (2025)
- [Embodied Science: Closing the Discovery Loop with Agentic Embodied AI](https://mlsanity.com/paper/2603.19782/) (2026)
- [CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning](https://mlsanity.com/paper/2512.05576/) (2025)
- [Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work](https://mlsanity.com/paper/2604.23674/) (2026)
- [TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment](https://mlsanity.com/paper/2604.23938/) (2026)
- [AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments](https://mlsanity.com/paper/2604.27725/) (2026)
- [An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES](https://mlsanity.com/paper/2605.02669/) (2026)
- [Ream: Unfolding Mutual Awareness in Human-Agent Workspaces](https://mlsanity.com/paper/2610.09497/) (2026)

## Abstract (arXiv)

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 https://aiscientist.tools.