RL2 min read
Sparse RL Relaxation for LLM Reasoning
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 multiple reasoning possibilities within a single…
By Jiabin Fan, Matthias Lindemann, Zita Marinho, Andr\'e FT Martins, Lili MouarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 21, 2026.
Comments
Sign in to join the discussion.