Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Charlie Snell, Jaehoon Lee, Kelvin Xu|August 6, 2024arXiv

Key Takeaway

Inference-time compute scaling is a viable alternative to model scaling — this paper provided the theoretical foundation for reasoning models like o1 and DeepSeek-R1.

Summary

Demonstrates that spending more compute at inference time (via search, verification, or repeated sampling) can be more efficient than training larger models. A smaller model with optimal test-time compute can match a 14x larger model.

reasoning scaling efficiency