TY  - RPRT
TI  - Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
AU  - Liu, D.
AU  - Yu, Y.
AU  - Wu, Y. N.
PY  - 2026
DO  - 10.64898/2026.05.10.724161
UR  - https://www.biorxiv.org/content/10.64898/2026.05.10.724161v1
ID  - 10.64898/2026.05.10.724161
ER  -