Efficient Thought Space Exploration Through Strategic Intervention
Ziheng Li, Hengyi Cai, Xiaochi Wei, Yuchen Li, Shuaiqiang Wang, Zhi-Hong Deng, Dawei Yin
Abstract
While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs through exhaustive sampling. Through analyzing decoding trajectories, we observe that most next-token predictions align well with the golden output, except for a few critical tokens that lead to deviations. Inspired by this phenomenon, we propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components: 1) a hinter (powerful LLM) that provides probabilistic guidance at critical decision points, and 2) a practitioner (efficient smaller model) that executes major reasoning steps. The framework
BibTeX
@inproceedings{aaai2026_efficientthought,
title = {Efficient Thought Space Exploration Through Strategic Intervention},
author = {Ziheng Li and Hengyi Cai and Xiaochi Wei and Yuchen Li and Shuaiqiang Wang and Zhi-Hong Deng and Dawei Yin},
booktitle = {AAAI 2026},
year = {2026}
}