A survey of slow thinking-based reasoning LLMs using reinforcement learning and test-time scaling law.

@article{pan-2026-survey, author = {Qianjun Pan and Wenkai Ji and Yuyang Ding and Junsong Li and Shilian Chen and Junyi Wang and Jie Zhou and Qin Chen and Min Zhang and Yulan Wu and Liang He}, title = {{A survey of slow thinking-based reasoning LLMs using reinforcement learning and test-time scaling law}}, journal = {Information Processing and Management}, volume = {63}, number = {2}, pages = {104394}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2025.104394}, doi = {https://doi.org/10.1016/J.IPM.2025.104394} }