CoTS: Competitive Token Selection for Latent Reasoning in Large Language Models
Competitive Token Selection (CoTS), a training-free framework that reframes latent intervention from binary mode selection into continuous allocation at the token level, and demonstrates that CoTS consistently outperforms standard CoT and state-of-the-art training-free latent reasoning methods.
Jie Yu, Yu-Xi Sun, Zhao-Xu Li et al.
· 0 citations