Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2601.10402/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTToward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering — mentioned by Xx_crazy420_xXhttps://news.ycombinator.com/item?id=47498739urn:hackerpapers:mention:2601.10402:47498739Tue, 24 Mar 2026 04:55:53 GMT<p>Autoresearch is nothing new, big players are already in the game with more sophisticated solutions: - https://arxiv.org/abs/2602.02660 (MARS) - https://arxiv.org/abs/2601.14525 (Execution-grounded automated AI research) - https://arxiv.org/abs/2601.10402 (ML-Master 2.0) The mostly used benchmark for automated AI engineering/ research is: https://github.com/openai/mle-bench</p><p><a href="https://hackerpaper.kaipfister.de/p/2601.10402/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.AI