I read a lot of papers I find on Google Scholar, and it's very common that they are wrong, or don't accurately survey related work, or pointless. For an overview of a field or a subfield, you want a review paper, and TAOCP is the best review of algorithms I've found. It's true that some of the volumes are outdated, but in many areas the new work is incremental.
Consider, as an example, Fascicle 5b, Introduction to Backtracking. His citations in the first 25 pages are from 1899, 1918, 2017, 1957, 1967, 1963, 1900, 1947, 1882, 1848, 1849, 1850, and 1960. Had he somehow managed to write this chapter in 01968 instead of 02019 he would only have been missing one of them, though surely the illustrations and experimental results of his own he reports would not have been as excellent, and surely the overall framing of the section benefits from the additional 61 years of hindsight.
In fact, although enormous progress has been made in backtracking in recent years, it hasn't affected the introductory aspects of the question. But clearly you can learn an enormous amount about backtracking without straying into the literature of the current millennium.
Consider, as an example, Fascicle 5b, Introduction to Backtracking. His citations in the first 25 pages are from 1899, 1918, 2017, 1957, 1967, 1963, 1900, 1947, 1882, 1848, 1849, 1850, and 1960. Had he somehow managed to write this chapter in 01968 instead of 02019 he would only have been missing one of them, though surely the illustrations and experimental results of his own he reports would not have been as excellent, and surely the overall framing of the section benefits from the additional 61 years of hindsight.
In fact, although enormous progress has been made in backtracking in recent years, it hasn't affected the introductory aspects of the question. But clearly you can learn an enormous amount about backtracking without straying into the literature of the current millennium.