# Principled Thoughts for Latent Recursive LLM Systems

**Published:** September 30, 2026
**Author:** Fahd Seddik, Fatemeh Fard
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/principled-thoughts-for-latent-recursive-llm-systems

arXiv:2609.36159v1 Announce Type: new Abstract: Large language models can reason in continuous space instead of decoded text, by recurring on their own hidden states or by passing those states between agents, while training supervises only the Cross-Entropy (CE) of the final…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.36159)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*