<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Latent-Space on Onur Baydaş</title><link>https://onurbaydas.com/en/tags/latent-space/</link><description>Recent content in Latent-Space on Onur Baydaş</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 19 Oct 2026 07:41:16 +0300</lastBuildDate><atom:link href="https://onurbaydas.com/en/tags/latent-space/index.xml" rel="self" type="application/rss+xml"/><item><title>Hybrid Reasoning Agents</title><link>https://onurbaydas.com/en/news/2026-10-19-hybrid-reasoning-agents-llm/</link><pubDate>Mon, 19 Oct 2026 07:41:16 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-19-hybrid-reasoning-agents-llm/</guid><description>Hybrid reasoning agents aim to speed up inference, use fewer tokens, and increase overall intelligence in LLMs. The core idea is to focus on processing in latent space rather than thinking in text.</description></item><item><title>Hybrid Reasoning Agents: LLM Agents Thinking in Latent Space, Acting Through Text</title><link>https://onurbaydas.com/en/news/2026-10-19-hybrid-reasoning-llm-agents/</link><pubDate>Mon, 19 Oct 2026 07:41:16 +0300</pubDate><guid>https://onurbaydas.com/en/news/2026-10-19-hybrid-reasoning-llm-agents/</guid><description>This news introduces a new LLM agent approach capable of thinking in latent space and performing text-based actions. Project details and source code are available via GitHub and Hugging Face.</description></item></channel></rss>