How to combine recommended lists produced by two different models?

Suppose there are two algorithms that I use to generate recommendations for a user, the first one producing list A, the second one producing list B, both of length $k$. Is there a clever way of combining the two lists (to create a hybrid approach, so to say) into a final list C of the same length as A and B? I suppose that some scoring could be possible, but I'm not sure what to base the scores on.

Another idea I had is the following: I have access to embedding vectors of items from both lists (A and B), so to extract the final list C I would look at the embedding and extract the items that are closest to the means of $k$ clusters found in the embedding space. Do you think it's a good idea? How would you utilize the items' embedding vectors?

Of course, a link to general literature address the above described issue is highly welcome.