1
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
实测大模型当超参优化顾问的真实战力:预算匹配下,起关键作用的是默认配置,而非LLM本身,结论含金量高但稍偏学术。
arXiv:2606.21641v1 Announce Type: cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "…