Learning Formal Mathematics From Intrinsic Motivation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2407.00695/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLearning Formal Mathematics From Intrinsic Motivation — mentioned by nielstronhttps://news.ycombinator.com/item?id=43981352urn:hackerpapers:mention:2407.00695:43981352Wed, 14 May 2025 06:08:47 GMT<p>we were thinking about doing exactly this, the closest current work is probably the amazing &quot;Learning Formal Mathematics from Intrinsic Motivation&quot; by Poesia et al (they use constraints too increase the likelihood of generating correct theorems/proofs during RL) https://arxiv.org/abs/2407.00695</p><p><a href="https://hackerpaper.kaipfister.de/p/2407.00695/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI