[Noumenon72]

Seems like you could train an LLM to read an op-ed and output the arguments in this form. Could be fun.

[viraptor]

Yes, it works really well in my experience. Although I mostly use it for technical information and justifying some decisions. But you can totally ask modern LLMs to "summarise this in ArgDown format" and they'll do the right thing.

[knallfrosch]

Just call an API and supply the JSON schema.

Though I doubt that arguments in this restricted form are more expressive than the original representation.