> renaming PDFs

Sorry, I didn't understand. Why do you need ML tool for renaming PDFs? or did you mean rephrasing or rewriting in a different format?

Maybe they mean walking a file tree and cleaning up file names to match the titles on the covers of them more accurately?

Exactly. You download something from arxiv and the filename has no meaningful content in it. Generally speaking, you want the filename to be descriptive in some way, extracting the title of the document is a good start.

You can just import them all into paperpile, which has good ways of inferring the metadata like title author year etc. and then connect to your google drive. Which will download them with nice filenames.

I tend to just select all the files and then paste their filenames into a Chat AI and tell it to write mv commands to rename them however I need. May be more complicated if you need it to open the PDF to get content for the rename though.