Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning
Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning
C. Snell,Jaehoon Lee,Kelvin Xu,Aviral Kumar
2025 · DBLP: conf/iclr/Snell0XK25
International Conference on Learning Representations · 164 Citations