It's a combination of GOFAI (fancy tree search) and ML (neural networks and differentiable programming)

The idea isn't particularly new but it wasn't possible to implement anything useful until recently when attention/transformers and LLMs gave a huge boost to NLP and most ML tasks.

The algorithms are generally in the area of machine learning + programming languages and pretty flexible. This paper talks about how we "bias" these algorithms for applications in the hard sciences (specifically talking about behavioral neuroscience but has/is being applied in other areas as well).