# Sparse RL Relaxation for LLM Reasoning

**Published:** October 21, 2026
**Author:** Jiabin Fan, Matthias Lindemann, Zita Marinho, Andr\'e FT Martins, Lili Mou
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/sparse-rl-relaxation-for-llm-reasoning

arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.27220)

**Tags:** #arXiv

---

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