让大模型推理更快更准，动态调整思考路径。
Dynamic Parallel Tree Search for Efficient LLM Reasoning
- 动态并行搜索框架，按需分配计算资源。
- 效率提升2-4倍，准确率不降反升。
- 适合需要高效推理的部署场景。
思维树（ToT）通过构建问题求解的树状结构来增强大语言模型的推理能力。然而，现有方法侧重于搜索准确性，忽视了计算效率。加速ToT的主要挑战在于频繁切换推理焦点以及对次优解的冗余探索。为此，我们提出动态并行树搜索（DPTS），一种新型并行化框架，旨在推理过程中动态优化思考路径。该框架在生成阶段引入并行化精简机制，通过细粒度缓存管理和对齐策略，实现灵活可调的任意路径并行。同时，搜索与转移机制筛选候选路径，动态维持对高潜力解的聚焦，减少冗余。在Qwen-2.5和Llama-3模型上，基于Math500和GSM8K数据集的实验表明，DPTS平均效率提升2-4倍，同时保持或超越现有推理算法的准确率，使基于ToT的推理更具可扩展性和计算效率。
原文摘要 · Abstract (English)
Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overlooking computational efficiency. The challenges of accelerating the ToT lie in the frequent switching of reasoning focus, and the redundant exploration of suboptimal solutions. To alleviate this dilemma, we propose Dynamic Parallel Tree Search (DPTS), a novel parallelism framework that aims to dynamically optimize the reasoning path in inference. It includes the Parallelism Streamline in the generation phase to build up a flexible and adaptive parallelism with arbitrary paths by fine-grained cache management and alignment. Meanwhile, the Search and Transition Mechanism filters potential candidates to dynamically maintain the reasoning focus on more possible solutions and have less redundancy. Experiments on Qwen-2.5 and Llama-3 with Math500 and GSM8K datasets show that DPTS significantly improves efficiency by 2-4x on average while maintaining or even surpassing existing reasoning algorithms in accuracy, making ToT-based reasoning more scalable and computationally efficient.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。