Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2405.00451/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTMonte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning — mentioned by ankit219https://news.ycombinator.com/item?id=42566819urn:hackerpapers:mention:2405.00451:42566819Wed, 01 Jan 2025 16:02:08 GMT<p>The other comment posted YT videos where Open AI researchers are talking about TTC. So, I am wrong. That $200 subscription is just because the number of tokens generated are huge when CoT is involved. Usually inference output is capped at 2000-4000 tokens (max of ~8192) or so, but they cannot do it with o1 and all the thinking tokens involved. This is true with all the approaches - next token prediction, TTC with beam/lookahead search, or MCTS + TTC. If you specify the output token range as high and induce a model to think before it answers, you will get better results on smaller/local models…</p><p><a href="https://hackerpaper.kaipfister.de/p/2405.00451/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI