MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering· MLExpert：面向通用自主开发的机器学习模型
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
面向通用自主开发的机器学习模型，实现AI自主改进。
- 核心方法
- 采用工作流驱动和模型指导交互的方法，从长时间交互轨迹中选择有效的监督信息，优化实验过程和策略。
- 适合谁读
- 研究者 / 工程师
- 要解决的问题
- 如何通过模型自主组织实验和优化策略，实现机器学习工程系统的长周期自主改进？
- 关键实验
- 未提供
- 主要贡献
- 提出了一种通用自主开发的机器学习模型（MLExpert），能够自主管理和优化复杂实验流程。
- 意义与局限
- 该模型为AI4AI提供了一条实现递归自我改进的实用路径，但需要解决长时间运行中实验成本高和监督选择难的问题。