系统梳理大模型推理中基于搜索的计算方法与框架
A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks
- 将任务统一建模为马尔可夫决策过程，明确推理框架结构
- 提出模块化定义，实现不同搜索算法间的精准对比
- 适合研究大模型推理优化、搜索算法设计的学者参考
基于搜索的大模型测试时计算（LLM test-time compute）已成为快速发展的研究方向。然而，现有框架在任务定义、大模型性能分析和搜索流程三个核心方面视角各异，导致直接比较困难。同时，所采用的搜索算法常偏离标准实现，其具体特性也未充分说明。本综述旨在对现有LLM推理框架进行系统性整合技术回顾。具体而言，我们统一以马尔可夫决策过程（MDP）定义任务，并提供模块化的LLM性能分析与搜索流程定义。该统一框架使不同推理方法间的精确比较成为可能，同时揭示其与传统搜索算法的差异。我们还讨论了这些方法的适用性、性能与效率。持续更新请访问我们的GitHub仓库：https://github.com/xinzhel/LLM-Search。
原文摘要 · Abstract (English)
LLM test-time compute (or LLM inference) via search has emerged as a promising research area with rapid developments. However, current frameworks often adopt distinct perspectives on three key aspects: task definition, LLM profiling, and search procedures, making direct comparisons challenging. Moreover, the search algorithms employed often diverge from standard implementations, and their specific characteristics are not thoroughly specified. This survey aims to provide a comprehensive but integrated technical review on existing LIS frameworks. Specifically, we unify task definitions under Markov Decision Process (MDP) and provides modular definitions of LLM profiling and search procedures. The definitions enable precise comparisons of various LLM inference frameworks while highlighting their departures from conventional search algorithms. We also discuss the applicability, performance, and efficiency of these methods. For ongoing paper updates, please refer to our GitHub repository: https://github.com/xinzhel/LLM-Search.
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。