paper-with-me

Papers

DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

2025-11-01 · Zicheng Xu, Xiuyi Lou, Guanchu Wang, Yu-Neng Chuang, Feng Luo, Guangyao Zheng, Alexander S. Szalay, Zirui Liu, Vladimir Braverman arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.00640

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Prompt Sketching for Large Language Models

2023-11-08 · Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin Vechev

Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder…

Arithmetic ReasoningBenchmarkingDecoderQuestion Answering+1

Sketching Merge Trees for Scientific Data Visualization

2021-01-08 · Mingzhe Li, Sourabh Palande, Lin Yan, Bei Wang

Merge trees are a type of topological descriptors that record the connectivity among the sublevel sets of scalar fields. They are among the most widely used topological tools in visualization. In this paper, we are inter…

Data Visualization

Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration

2026-01-02 · Longxuan Wei, Yubo Zhang, Zijiao Zhang, Zhihu Wang 외 arxiv

Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based dec…

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

2024-03-30 · Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You 외

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, spec…

GPU

STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering

2024-07-04 · Zhenyu Bi, Daniel Hajialigol, Zhongkai Sun, Jie Hao 외

Multi-hop question answering (MHQA) requires a model to retrieve and integrate information from multiple passages to answer a complex question. Recent systems leverage the power of large language models and integrate evi…

HallucinationMulti-hop Question AnsweringQuestion Answering