← 返回论文库
MLR-Copilot: Autonomous Machine Learning Research based on LLM Agents
Ruochen Li, Teerth Patel, Qingyun Wang, Xinya Du · 2024
L0.4 · Financial AgentsarXiv:2408.14033#research-agent
CORE IDEA
把 ML research 拆成 4 阶段（Idea→Experimentation→Implementation→Analysis），每阶段一个专门 agent。
CONCRETE EXAMPLE
在 5 个 ML benchmark 上自主完成 hypothesis-to-paper 流程。
L-ANCHOR · 为什么在这一层重要
L0.4 → L1 桥梁，ML research agent 范式
相关论文
RD-Agent(Q): Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
Beyond Prompting: Autonomous Systematic Factor Investing
AI Scientist v1: Towards Fully Automated Open-Ended Scientific Discovery
AI Scientist v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search