English

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

Artificial Intelligence 2026-02-05 v2 Computation and Language Machine Learning

Abstract

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to uncover high-quality solutions. To address these limitations, we propose Decoding Tree Sketching (DTS), a plug-and-play decoding framework for structural multi-trajectory exploration and reasoning selection. For reasoning exploration, DTS sketches a backbone tree of the reasoning space by selectively branching at decision tokens. For reasoning selection, guided by length-accuracy anti-correlation, DTS designs an early termination to prioritize short and reliable trajectories during decoding. Experimental results across four LRMs and datasets demonstrate that DTS significantly enhances accuracy by 14% and reduces repetitive generation by 8% on average. Notably, DTS enables smaller models to outperform larger models with 10×\times the size, highlighting its potential to strengthen reasoning capabilities.

Keywords

Cite

@article{arxiv.2511.00640,
  title  = {DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching},
  author = {Zicheng Xu and Xiuyi Lou and Guanchu Wang and Yu-Neng Chuang and Feng Luo and Guangyao Zheng and Alexander S. Szalay and Zirui Liu and Vladimir Braverman},
  journal= {arXiv preprint arXiv:2511.00640},
  year   = {2026}
}
R2 v1 2026-07-01T07:17:17.666Z