Definitely a combination of current ML (basically fancy nonlinear regression to MLE targets) with symbolic reasoning. Either alone are insufficient.
Symbolic reasoning is basically learning a lot of "if-then" statements and chaining them to make inference. Causal reasoning consists of defining conditional dependencies of current state on past state, then extrapolating based on the encoded assumptions. It requires some notion of object relation both in a literal sense as well as subtler relationships. Regression techniques are being ham-fisted to fit these roles but the popular ML of today is still just pattern recognition and cannot be called "reasoning" per se.
I don't work directly in this space but I see it following closely the architecture of the human brain for a while before departing to more distilled forms of knowledge management structures.
Neural networks do exactly what you are describing as "symbolic reasoning". It seems to be a common thing recently to dismiss modern ML techniques as curve fitting, but these fundamental models are extremely powerful.
Neural networks are capable of approximating any system to arbitrary precision.
This is theoretically true, but it's like saying "computers can compute any function, given enough time and resources".
There is a need to construct logically-deduced models which impose an inductive bias so that your regression methods are efficient. That's where reasoning comes in, and where automated reasoning methods should be useful.
Symbolic reasoning is basically learning a lot of "if-then" statements and chaining them to make inference. Causal reasoning consists of defining conditional dependencies of current state on past state, then extrapolating based on the encoded assumptions. It requires some notion of object relation both in a literal sense as well as subtler relationships. Regression techniques are being ham-fisted to fit these roles but the popular ML of today is still just pattern recognition and cannot be called "reasoning" per se.
I don't work directly in this space but I see it following closely the architecture of the human brain for a while before departing to more distilled forms of knowledge management structures.