That sounds like future work for simulated annealing fans to engage in, quite honestly, rather than something that needs to be addressed immediately in a paper proposing an alternative method. The proposed method accomplished what it set out to do, surpassing current methods; others are free to explore different hyperparameters to surpass the quality again... This is, ultimately, why we build benchmark tasks: if you want to prove you know how to do it better, one is free to just go do it better instead of whining about what the competition did or didn't try on one's behalf.
