Rethinking Inference-Time Scaling: Efficiency Limits and Linguistic Signals

Understand

There is intense interest in investigating how inference time compute (ITC) (e.g.

• repeated sampling, refinements, etc) can improve large language model (LLM) capabilities.
• While breakthroughs like DeepSeek-R1 highlight the power of reinforcement learning for reasoning, the interaction between ITC and reasoning-optimized weights remains poorly understood.
• This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models on challenging reasoning tasks.