AI RESEARCH
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
arXiv CS.AI
•
ArXi:2505.23723v2 Announce Type: replace-cross The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the capacity to learn from execution trajectories for generalization, while large