Guided Speculative Inference for Efficient Test-Time Alignment of LLMs
Jonathan Geuter, Youssef Mroueh, David Alvarez-Melis
Abstract
We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided decoding in large language models. GSI combines soft best-of-$n$ test-time scaling with a reward model $r(x,y)$ and speculative samples from a small auxiliary model $\pi_S(y\mid x)$. We provably approximate both the optimal tilted policy $\pi_{\beta,B}(y\mid x) \propto \pi_B(y\mid x)\exp(\beta\,r(x,y))$ of soft best-of-$n$ under the base model $\pi_B$, as well as the expected reward under the optimal policy. In experiments on reasoning benchmarks (MATH500, OlympiadBench, Minerva Math, MMLU-STEM, GSM8K) and across different model families, our method achieves higher accuracy than standard soft best-of-$n$ with $\pi_S$ and reward-guided speculative decoding (Liao et al., 2025), and in certain settings even outperforms soft best-of-$n$ with $\pi_B$, while reducing end-to-end latency by up to 28%.
BibTeX
@inproceedings{
geuter2026guided,
title={Guided Speculative Inference for Efficient Test-Time Alignment of {LLM}s},
author={Jonathan Geuter and Youssef Mroueh and David Alvarez-Melis},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=miNzDqDENd}
}