DoctorAgents：面向小型临床时间数据的智能体AutoML框架
原标题：DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data
AI 摘要
DoctorAgents是一个为小型临床时间序列数据设计的智能体框架，通过专门的LLM智能体（生成、验证、优化）将AutoML从穷举搜索转变为推理驱动的迭代优化。它利用文本梯度下降反向传播自然语言反馈，无需穷举搜索即可进行针对性更新。实验表明，DoctorAgents在多种临床任务上优于现有AutoML基线，并生成更可解释的任务特定表示。
正文节选
Computer Science > Artificial Intelligence Title:DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data View PDF HTML (experimental) Abstract:Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce, heterogeneous, and temporal complexity. Developing effective ML pipelines for such data remains time-consuming and error-prone, while existing