LADDER: Self-Improving LLMs Through Recursive Problem Decomposition · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2503.00735/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTLADDER: Self-Improving LLMs Through Recursive Problem Decomposition — HN submissionhttps://news.ycombinator.com/item?id=43287821urn:hackerpapers:submission:2503.00735:43287821Fri, 07 Mar 2025 06:45:57 GMT<p>Ladder: Self-improving LLMs through recursive problem decomposition</p><p></p><p>370 points; 110 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2503.00735/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG