外观
论文arXiv 2610.2234413 天前
MLExpert：迈向用于自主机器学习工程的通用智能体模型
原文链接：MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering（arXiv 2610.22344 · 发布日期：2026-10-15）
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
针对长程自主机器学习工程优化，提出后训练方法训练MLExpert，并在MLE-Bench Lite等任务上验证。
核心要点
- 长程MLE运行包含许多高成本实验，训练需从长交互轨迹中选择有效监督并学习中间结果。
- 方法构建Kaggle-MLE Factory，并结合分层agentic SFT与Windowed Interaction RL进行训练。
- 在MLE-Bench Lite上，MLExpert将基础模型平均奖牌率从37.9%提升至72.7%。
- 进一步实验显示，其优化能力可迁移到NatureBench Lite、agent scaffold优化和算法优化。
验证范围与局限：验证范围限于摘要所述MLE-Bench Lite、NatureBench Lite、agent scaffold优化和算法优化实验。
英文摘要 (Abstract)
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE) systems provide a practical path toward this pursuit through complex orchestration that manages long-horizon experimentation, while recent MLE systems adopt model-directed interaction, allowing models to autonomously organize experiments and adapt optimization strategies based on execution feedback. However, feedback from each experiment reflects several preceding decisions, and a long MLE run contains many such costly experiments. Training must therefore select useful supervision from long interaction trajectories and learn from intermediate outcomes. We propose a post-training method for autonomous long-horizon MLE optimization and apply it to train MLExpert, a 35B Mixture-of-Experts agentic model. We design the Kaggle-MLE Factory to construct executable tasks and an interaction harness for model-directed experimentation. Hierarchical agentic SFT transfers general tool-use and coding capabilities to MLE through outcome-guided supervision. Windowed Interaction RL (WIRL) treats the multi-turn decisions between successive experiment results as an execution window and assigns it a shared outcome-based reward. Asynchronous collection and policy correction support policy updates before the trajectory ends. On MLE-Bench Lite, MLExpert improves the average medal rate of the base model from 37.9% to 72.7%, achieving performance comparable to larger frontier models such as Kimi-K3 and GLM-5.3. Further experiments show that MLExpert improves performance on NatureBench Lite, agent scaffold optimization, and algorithm optimization, suggesting that the learned optimization capability generalizes to other tasks.
作者：Shangheng Du, Jinxin Shi, Shuaiyu Zhang, Yiming Wu, Junpeng Zhao, Shiyang Feng, Xin Li, Liang He, Xiangchao Yan, Bo Zhang
来源
本页事实对应的公开页面，以原文为准。