MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2205.00445/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTMRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning — mentioned by avereveardhttps://news.ycombinator.com/item?id=35529885urn:hackerpapers:mention:2205.00445:35529885Tue, 11 Apr 2023 19:12:20 GMT<p>original paper: https://arxiv.org/abs/2205.00445 langchain agents are a good starting implementation. you can build your own prompt and get the ai to work by iself hallucinating tools, which may be cheaper to test out than going back and forth with an agent manager. not as accurate, but you can still extract useful work, i.e. https://i.imgur.com/AE4R3dR.png (gpt-35-turbo is traditionally failing this task completely, prompt get it to work at it) these prompt all require the model to work off data within the prompt within the first shoot. model require a degree to introspection for that to…</p><p><a href="https://hackerpaper.kaipfister.de/p/2205.00445/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL