不重训模型，用推理时计算提升大模型表现
Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
- 分输出与输入两类策略，利用推理阶段计算增强性能
- 检索增强生成（RAG）为核心，涵盖查询扩展与多模态支持
- 适合想提升模型效果又不想重训练的开发者
大模型性能提升长期依赖模型规模和训练数据扩大。但高质量训练数据日益稀缺，成为瓶颈，研究重心转向推理时扩展。该范式通过部署时增加计算量，在不重新训练模型的前提下显著提升下游任务表现。本文系统梳理这一新兴领域，将技术分为两大类：输出导向型（如思维链、搜索解码、强化学习训练长思维链、模型集成）与输入导向型（以少样本和检索增强生成为主，重点分析查询扩展、数据、检索与重排序、生成方法及多模态RAG）。
原文摘要 · Abstract (English)
The performance gains of LLMs have historically been driven by scaling up model size and training data. However, the rapidly diminishing availability of high-quality training data is introducing a fundamental bottleneck, shifting the focus of research toward inference-time scaling. This paradigm uses additional computation at the time of deployment to substantially improve LLM performance on downstream tasks without costly model re-training. This review systematically surveys the diverse techniques contributing to this new era of inference-time scaling, organizing the rapidly evolving field into two comprehensive perspectives: Output-focused and Input-focused methods. Output-focused techniques encompass complex, multi-step generation strategies, including reasoning (e.g., CoT, ToT, ReAct), various search and decoding methods (e.g., MCTS, beam search), training for long CoT (e.g., RLVR, GRPO), and model ensemble methods. Input-focused techniques are primarily categorized by few-shot and RAG, with RAG as the central focus. The RAG section is further detailed through a structured examination of query expansion, data, retrieval and reranker, LLM generation methods, and multi-modal RAG.
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。