Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
130 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
36 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
4 tokens/sec
DeepSeek R1 via Azure Pro
33 tokens/sec
2000 character limit reached

Accelerated Test-Time Scaling with Model-Free Speculative Sampling (2506.04708v1)

Published 5 Jun 2025 in cs.CL

Abstract: LLMs have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating a critical trade-off between performance and efficiency. We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach that leverages the inherent redundancy in reasoning trajectories to achieve significant acceleration without compromising accuracy. Our analysis reveals that reasoning paths frequently reuse similar reasoning patterns, enabling efficient model-free token prediction without requiring separate draft models. By introducing stochastic drafting and preserving probabilistic information through a memory-efficient logit-based N-gram module, combined with optimized Gumbel-Top-K sampling and data-driven tree construction, STAND significantly improves token acceptance rates. Extensive evaluations across multiple models and reasoning tasks (AIME-2024, GPQA-Diamond, and LiveCodeBench) demonstrate that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding while maintaining accuracy. Furthermore, STAND outperforms state-of-the-art speculative decoding methods by 14-28% in throughput and shows strong performance even in single-trajectory scenarios, reducing inference latency by 48-58%. As a model-free approach, STAND can be applied to any existing LLM without additional training, being a powerful plug-and-play solution for accelerating LLM reasoning.

Summary

We haven't generated a summary for this paper yet.

Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.