Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG

• URL: http://arxiv.org/abs/2510.10787v1
• Date: Sun, 12 Oct 2025 20:09:07 GMT
• Title: Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
• Authors: Zhichao Wang, Cheng Wan, Dong Nie,
• Abstract summary: Performance gains of LLMs have historically been driven by scaling up model size and training data.<n>The rapidly diminishing availability of high-quality training data is introducing a fundamental bottleneck.<n>This review systematically surveys the diverse techniques contributing to this new era of inference-time scaling.
• Score: 13.772025442106544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning [20.48365890565577]
  We propose a novel meta-RLVR algorithm that dynamically selects training data at each step based on the average response length.<n>We evaluate LSPO across multiple base models and datasets, demonstrating that it consistently improves learning effectiveness.
  arXiv  Detail & Related papers  (2025-10-01T20:57:22Z)
• Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval [5.640810636056805]
  MoLER is a domain-aware RAG method that uses MoL-Enhanced Reinforcement Learning to optimize retrieval.<n>MoLER bridges the knowledge gap in RAG systems, enabling robust and scalable retrieval in specialized domains.
  arXiv  Detail & Related papers  (2025-09-08T13:04:07Z)
• Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning [53.85659415230589]
  This paper systematically reviews widely adoptedReinforcement learning techniques.<n>We present clear guidelines for selecting RL techniques tailored to specific setups.<n>We also reveal that a minimalist combination of two techniques can unlock the learning capability of critic-free policies.
  arXiv  Detail & Related papers  (2025-08-11T17:39:45Z)
• Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies [66.83950068218033]
  Scaling Laws demonstrate that scaling model parameters and training data enhances learning performance.<n>Despite its potential to improve performance, the integration of scaling laws into deep reinforcement learning has not been fully realized.<n>This review addresses this gap by systematically analyzing scaling strategies in three dimensions: data, network, and training budget.
  arXiv  Detail & Related papers  (2025-08-05T08:03:12Z)
• Taming the Titans: A Survey of Efficient LLM Inference Serving [33.65474967178607]
  Large Language Models (LLMs) for Generative AI have achieved remarkable progress.<n>The substantial memory overhead caused by their vast number of parameters, combined with the high computational demands of the attention mechanism, poses significant challenges.<n>Recent advancements, driven by groundbreaking research, have significantly accelerated progress in this field.
  arXiv  Detail & Related papers  (2025-04-28T12:14:02Z)
• Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning [19.64843401617767]
  In this paper, we introduce HRLFS, a reinforcement learning-based subspace exploration strategy for complex datasets.<n>We show that HRLFS improves the downstream machine learning performance with iterative feature subspace exploration.<n>We also show that HRLFS accelerates total run time by reducing the number of agents involved.
  arXiv  Detail & Related papers  (2025-04-24T08:16:36Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models generate target documents directly from a query.<n>We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization [18.703421169342796]
  This work proposes a framework capable of simultaneously evolving several DQL models towards solving interrelated Reinforcement Learning tasks. A thorough experimentation is presented and discussed so as to assess the performance of the framework.
  arXiv  Detail & Related papers  (2020-02-25T10:36:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.