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 a superposition of m…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.AI
Sparse RL Relaxation for LLM Reasoning