ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2312.10003/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent — HN submissionhttps://news.ycombinator.com/item?id=38722880urn:hackerpapers:submission:2312.10003:38722880Thu, 21 Dec 2023 16:45:46 GMT<p>ReST Meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent</p><p></p><p>3 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/2312.10003/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL