DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

📝 Original Info

• Title: DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching
• ArXiv ID: 2511.00640
• Date: 2025-11-01
• Authors: ** 해당 논문에 명시된 저자 정보가 제공되지 않았습니다. (Authors: 정보 없음) **

📝 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.

💡 Deep Analysis

📄 Full Content

Reference