Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters
Snell et al., 2025, Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters (The Thirteenth International Conference on Learning Representations (ICLR 2025))
Subscriber deck — free during early access
1 cards in “6.2 Analysis Results: Test-Time Scaling with Revisions” · whole deck
6.2 Analysis Results: Test-Time Scaling with Revisions
- How should compute be split between sequential revisions and parallel samples?It depends on difficulty: easy questions do best with purely sequential revisions (local refinement of an answer that is nearly right), harder ones with a balance of revisions and parallel samples (global search over different approaches).
The best mix depends on how hard the question is for the base model - Snell et al., 2025, Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters (The Thirteenth International Conference on Learning Representations (ICLR 2025)), §6.2
Source
- Charlie Snell, Jaehoon Lee, Kelvin Xu and Aviral Kumar. 2025. Scaling LLM Test-Time Compute Optimally Can Be More Effective than Scaling Model Parameters. In The Thirteenth International Conference on Learning Representations (ICLR 2025). https://arxiv.org/abs/2408.03314