What's the point. I don't know that

I like this nice concise function syntax!

Pointfree go brrrrr...

Should have had

levels = (1, [1..b-1]) : [(l+1, concatMap (generate (l+1)) prefix) | (l, prefix) <- levels, not (null prefix)]

The orignal will be left forever joining an infinite stream of empty lists, when there are no more polydivisible numbers available.

What am I even looking at?

wtf

Oh my... That's amazing :)

Zero-length edges would merit a mention in the description; they would be somewhat counterintuitive.

Fixed testing with adjacent parallel edges would be nice though.

You should add more edge cases to the tests, such as adjacent parallel edges and zero-length edges.

Random tests are producing false negatives:

Falsifiable (after 74 tests and 37 shrinks): 
[(-37,[-2,51]),(-2,[-37]),(51,[-37,-2]),(-2,[51])]
3 /= 2

Falsifiable (after 27 tests and 18 shrinks): 
[(17,[17]),(17,[17])]
1 /= 2

Falsifiable (after 28 tests and 30 shrinks): 
[(23,[-20]),(-7,[23,-20]),(23,[-7]),(-20,[-7]),(-20,[23])]
3 /= 2

Falsifiable (after 61 tests and 37 shrinks): 
[(-2,[-51,18]),(18,[-51]),(-51,[-2,18]),(18,[-2])]
3 /= 2

The specification is ambiguous. I believe that assumption was the intent of the author because my solution passes all the tests, and there are no counterexamples given in the specification.

This seems to assume that there are no characters after any closing parenthesis. The specification only mentions the last closing parenthesis.

its clever though, right?

Don't worry, it will fail the performance version of the kata.

How is this a best practice with an exponential running time and memory consumption?