AI 中文总结
该研究推出面向MLE中RSI研究的开源全栈系统OpenMLE，后训练Frontis-MA1（35B）作为元进化智能体，在多个基准测试中提升性能，相关模型与系统已开源。
AI 中文摘要
递归自我改进（RSI）需要能够改进AI构建过程（即AI4AI）的AI系统，机器学习工程（MLE）为研究该能力提供了具体、可执行的测试平台。我们推出OpenMLE，这是一个面向MLE中RSI研究的开源全栈系统，涵盖带执行反馈的可验证任务环境（OpenMLE-Gym）、算子学习（OpenMLE-RL）和长程搜索（OpenMLE-Evo）。在该栈上，我们后训练Frontis-MA1（35B）作为MLE的元进化智能体，围绕四个原子程序进化算子（Draft、Improve、Debug、Crossover）对齐后训练与推理：通过基于执行的SFT和RL在针对所有评估基准去重的数据上训练相同算子，再将其组合成长程搜索，在单个循环中耦合学习与进化。在MLE-Bench Lite上，单块RTX 4090的12GB显存上限下，每任务预算12小时，Frontis-MA1（35B）结合OpenMLE-Evo将Medal Average从基础模型的39.39%提升至60.61%，结合OpenMLE-Evo-Max（基准无关经验先验与异步搜索）则达到71.21%，超过GPT-5.5 + Codex，接近GPT-5.6 Sol和2.8T Kimi K3。在保留的NatureBench Lite上，两部分均具备迁移性：框架固定时，替换为训练后的模型将Match-SOTA从50%提升至70%；模型固定时，替换为OpenMLE-Evo将其从20%提升至50%。我们发布模型权重和完整OpenMLE栈，以支持面向RSI的可执行AI4AI的可复现研究。代码：this https URL
英文摘要
Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introduce OpenMLE, an open full-stack system for RSI research in MLE, spanning verifiable task environments with execution feedback (OpenMLE-Gym), operator learning (OpenMLE-RL), and long-horizon search (OpenMLE-Evo). On this stack we post-train Frontis-MA1 (35B) as a meta-evolution agent for MLE, aligning post-training and inference around four atomic program-evolution operators (Draft, Improve, Debug, Crossover): the same operators are trained via execution-grounded SFT and RL on data deduplicated against all evaluation benchmarks, then composed into long-horizon search, coupling learning and evolution in a single loop. On MLE-Bench Lite under a 12-hour per-task budget on one RTX 4090 capped at 12 GB VRAM, Frontis-MA1 (35B) improves Medal Average from 39.39% to 60.61% over its base model with OpenMLE-Evo, and reaches 71.21% with OpenMLE-Evo-Max (benchmark-independent experience priors and asynchronous search), exceeding GPT-5.5 + Codex and approaching GPT-5.6 Sol and the 2.8T Kimi K3. On held-out NatureBench Lite, both components transfer: with the framework fixed, swapping in the trained model raises Match-SOTA from 50% to 70%; with the model fixed, swapping in OpenMLE-Evo raises it from 20% to 50%. We release the model weights and the full OpenMLE stack to enable reproducible research on executable AI4AI toward RSI. Code: https://github.com/FrontisAI/OpenRSI
