Kim, J., Wu, D., Lee, J., & Suzuki, T. (2025). Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation.
Cita Chicago Style (17a ed.)Kim, Juno, Denny Wu, Jason Lee, y Taiji Suzuki. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation. 2025.
Cita MLA (9a ed.)Kim, Juno, et al. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation. 2025.
Precaución: Estas citas no son 100% exactas.