An alternative approach, Generative Adversarial Networks (GANs), has become popular across severaldomains, particularly Computer Vision, owing tobreakthrough realism intheimages they output[e.g.,19,65]. This is the case in NLP where, unlike computer vision, a measure of likelihood called perplexityhas been theprevailing metric fortraining and evaluating language models fordecades.

In order to build more useful AI systems, a natural inclination is to try to make them more agentic . But while agents built from language models are touted as the next big advance [Wang et al., 2024],

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation.

Bayesian optimization (BO) conventionally relies on handcrafted acquisition functions (AFs) to sequentially determine the sample points. However, it has been widely observed in practice that the best-performing AF in terms of regret can vary significantly under different types of black-box functions. It has remained a challenge to design one AF that can attain the best performance over a wide variety of black-box functions.