为什么值得关注

这是面向机器学习工程中递归自我改进的开放全栈尝试之一，公开模型权重、可执行的 Gym/SFT/RL/Evo 流水线与数据集，并通过受控对比将后训练收益和搜索系统收益分开衡量。

适合谁使用

研究 AI4AI 或递归自我改进（RSI）的研究人员
需要可复现程序演化管线的机器学习工程实践者
构建可执行研究任务与评测基准的开发者
关注模型后训练、强化学习或进化搜索的开源开发者

典型使用场景

在 MLE-Bench Lite 或 NatureBench Lite 上复现 Frontis-MA1 结果
使用 OpenMLE-Gym 构建和评测可验证的机器学习工程任务包
运行 OpenMLE-Evo 进行标准或异步长 horizon 搜索
使用 OpenMLE-ERL 的 SFT/RL 流程训练程序演化算子

项目优势

开源模型权重、OpenMLE 技术栈和数据集（Frontis-MA1、OpenMLE Tasks、SFT Traces）
受控对比区分模型后训练与搜索系统贡献（MLE-Bench Lite 上 39.39% → 60.61%，并迁移到 NatureBench）
以执行反馈训练 Draft、Improve、Debug、Crossover 四个原子算子，统一后训练与推理
各组件提供独立 README 和文档，覆盖任务构建、训练、启动与验证

使用前须知

采用 CC BY-NC 4.0 许可，未授予商业使用权利
首次发布，作者未声称解决通用递归自我改进；报告结果为模型-搜索框架联合结果，而非单次模型得分
外部基准环境、服务凭证和部分基础设施需要与仓库分开获取

README 快速开始

OpenRSI by Frontis

Making “AI improving AI” executable, measurable, and reproducible.

🌐 Project Page · 📄 Paper · 🤗 Frontis-MA1 Collection · 🧩 OpenMLE Tasks · 🎬 Frontis-MA1 Video

📖 OpenRSI · 🚀 Frontis-MA1 · 🧩 OpenMLE · 📊 Results · ✨ Getting Started · 🤝 Contribute

FIRST RELEASE · MACHINE LEARNING ENGINEERING Frontis-MA1 + OpenMLE

📰 News

[2026-07-31] 🎉 First OpenRSI release: Frontis-MA1 (35B / 30B, with GGUF derivatives), the OpenMLE stack (Gym / RL / Evo), and the OpenMLE Tasks and OpenMLE SFT Traces datasets.
[2026-06-23] 📄 We released NatureBench: NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers? (code) — a benchmark testing whether coding agents can match the published SOTA of Nature-family papers, later used as the held-out transfer benchmark for Frontis-MA1.

📖 OpenRSI

OpenRSI is Frontis's open initiative for turning “AI improving AI” into an executable engineering problem. It develops AI4AI systems through three connected routes:

AI4AI foundation models that internalize reusable research processes
World models and research taste that identify where additional compute is worth spending
Open tasks, environments, and evaluations that convert real research into scalable training and search pipelines

Search produces experience, experience enters training, and trained models ret

项目描述

Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

lopopolo

精选

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI 与机器学习AI 智能体

2,390

slvDev

精选

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI 与机器学习大语言模型

1,960

littledivy

精选

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI 与机器学习

1,482