发表机构
AI Institute, University of Waikato; LTCI, Télécom Paris, Institut Polytechnique de Paris（怀卡托大学人工智能研究所; 巴黎高等电信学校LTCI实验室，巴黎综合理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TuiML是一个为AI智能体设计的自包含机器学习库，通过机器可读元数据和验证工作流，使智能体能自主搜索、组合和扩展算法，同时保持与scikit-learn和Weka相当的预测性能。
AI 中文摘要
Weka和scikit-learn等机器学习库是为人类程序员设计的。语言模型智能体现在通过从记忆中回忆API并编写代码来使用这些库，这种方法隐藏了库所提供的功能，将错误延迟到运行时，并在轮次之间丢失实验状态。我们提出TuiML，一个为AI智能体构建的自包含机器学习库，在监督学习、无监督学习、时间序列、数据处理、调优和评估任务中提供原生算法。每个组件通过机器可读的元数据和参数模式描述自身，使智能体能够搜索库、检查组件、组合经过验证的工作流，并注册新的组件，这些新组件随后也可被发现。每次调用都经过验证、设定种子并追踪，会话导出为可运行的笔记本，使实验从构造上可复现。一个规范层驱动模型上下文协议（MCP）、智能体框架适配器、Python API、CLI和本地模型服务，而数据和模型永远不会离开机器。基准测试表明，TuiML在预测性能上与scikit-learn和Weka保持竞争力。虽然对人工用户来说看起来像一个传统库，但TuiML首先是为智能体设计的，允许它们自主地读取、扩展和操作机器学习。TuiML是开源的，文档位于此HTTPS URL。
英文摘要
Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by recalling APIs from memory and writing code, an approach that hides what a library offers, delays errors until runtime, and loses experimental state between turns. We present TuiML, a self-contained machine-learning library built for AI agents, with native algorithms across supervised, unsupervised, time-series, data handling, tuning, and evaluation tasks. Every component describes itself through machine-readable metadata and parameter schemas, so an agent can search the library, inspect components, compose validated workflows, and register new ones that become discoverable in turn. Every call is validated, seeded, and traced, and sessions export as runnable notebooks, making experiments reproducible by construction. One specification layer drives the Model Context Protocol (MCP), agent-framework adapters, a Python API, a CLI, and local model serving, while data and models never leave the machine. Benchmarks show TuiML remains predictively competitive with scikit-learn and Weka. While looking like a conventional library to a human user, TuiML is designed for agents first, allowing them to read, extend, and operate machine learning autonomously. TuiML is open source, with documentation at https://tuiml.ai.
Comments8 pages, 3 figures. Code and documentation at https://tuiml.ai
