There's active work on this (although in two separate strands of research).

The first is multi-document summarization. Back in 2018 Google published Generating Wikipedia by Summarizing Long Sequences[1] which did a great job of combining multiple pages into a single Wikipedia-like document. Models have strengthened a lot since then so it should be possible to do better, but I haven't seen any work.

There's also a bunch of work on summarization of a single document into a few sentences.

The second piece of research work is Question Answering. There are multiple directions for that, but looking at recent work on the SQUAD 2.0 leaderboard should give you a good idea of what is possible[2].

Basically, combining these systems should work quite well a lot of the time.

[1] https://arxiv.org/abs/1801.10198

[2] https://rajpurkar.github.io/SQuAD-explorer/

Actually just ran into this [1] today. Not production ready, but you could hack something together with it. It was even trained on Wikipedia articles.

[1]: https://rajpurkar.github.io/SQuAD-explorer/

i've thought of this many times. "Wikibot, tell me more about bridges of the 19th century." <blah blah summary> "Stop. Tell me more the Ponte delle Catene, Bagni di Lucca bridge" <blah blah details>

Even simpler, I wanted my iPhone to read a wikipage out loud to me while I was walking home in the cold, and I was surprised that I couldn't figure it out - you can switch on the screen reader in accessibility, but it stopped reading after half a paragraph. Very annoying.

Like most things in ML, the technological exists and theoretically works, but ymmv in production.