Hybrid Reasoning Agents: thinking in latent space, acting through text

Jiaru "Rubin" Zou @Jiaru_ZouOriginally posted 2026.10.15

Open original on X

Your LLM agent has to think out loud, token by token, before it can search, run code, or act in the world. We humans don’t. We ponder in silence and speak when it matters. Human language was never meant to be the limit of machine thought. Introducing 🌗Hybrid Reasoning Agents - Think in latent space, act through text - Two modes, one unified multi-turn flow - No black box, fully readable latent thoughts - Any LLM can become a HybridAgent