SpecExit: Accelerating Large Reasoning Model via Speculative Exit

Rubing Yang, Huajun Bai, Song Liu, Guanghua Yu, Runzhi Fan, Yanbin Dang, Zhang Jiejing, Kai Liu, Jianchen Zhu, Peng Chen

Keywords: efficient reasoning, speculative decoding

Abstract: Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world deployment. To address overthinking, early-exit mechanisms have been proposed to terminate reasoning before typical completion, showing that this approach can effectively shorten generation length with minimal impact on accuracy. However, their reliance on probing mechanisms introduces a detection overhead that limits their end-to-end latency gains and compromises their generalizability across diverse problems. Inspired by the use of hidden states in speculative decoding, we propose \textbf{SpecExit}, a novel framework that predicts both future tokens and an early-exit signal directly from a lightweight draft model without probing overhead. Our method offers significant improvements, achieving up to 66% generation length reduction and 2.5× end-to-end speedup compared with the speculative decoding baseline, without compromising accuracy. Our method leverages the inherent signals from hidden states to provide effective early-exit signals, suggesting broader use of hidden states for efficient reasoning. Our code is available at: https://anonymous.4open.science/r/SpecExit-B802.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 3950