检索增强生成论文趋势 2023–2026

主要结论

• 检索增强生成论文从 2023 年的 102 篇增长到 2026 年的 549 篇，三年间扩大到约 5.4 倍。
• NeurIPS 是发检索增强生成论文最多的会议，2023–2026 年共 391 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 75 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的代码生成是 4.1 倍，检索增强生成是 5.4 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
• ICLR 2026AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM Serving
• CVPR 2026ADSeeker A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and
• NeurIPS 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
• ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
• ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
• CVPR 2025AirRoom: Objects Matter in Room Reidentification
• NeurIPS 2024$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
• ICML 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
• ICLR 2024BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
• CVPR 2024Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods
• NeurIPS 2023A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance
• ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
• ICLR 2023Decompositional Generation Process for Instance-Dependent Partial Label Learning
• CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
• NeurIPS 2026Accelerating Neural Network Training with Augmented Koopman Dynamics
• ICML 2026$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
• ICLR 2026Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency Graph
• CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

全部检索增强生成论文

共 102 篇，第 2 / 3 页

51. ICLR 2023kNN-Diffusion: Image Generation via Large-Scale Retrieval
52. ICLR 2023KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals
53. ICLR 2023Learning the Positions in CountSketch
54. ICLR 2023Learning to Generate Columns with Application to Vertex Coloring
55. ICLR 2023LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval
56. ICLR 2023Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval
57. ICLR 2023Neural Networks and the Chomsky Hierarchy
58. ICLR 2023On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
59. ICLR 2023Promptagator: Few-shot Dense Retrieval From 8 Examples
60. ICLR 2023Re-Imagen: Retrieval-Augmented Text-to-Image Generator
61. ICLR 2023Recitation-Augmented Language Models
62. ICLR 2023Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
63. ICLR 2023Retrieval-based Controllable Molecule Generation
64. ICLR 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
65. ICLR 2023The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
66. ICLR 2023wav2tok: Deep Sequence Tokenizer for Audio Retrieval
67. ICML 2023Automatic Data Augmentation via Invariance-Constrained Learning
68. ICML 2023Coder Reviewer Reranking for Code Generation
69. ICML 2023Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching
70. ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
71. ICML 2023Exploring Chemical Space with Score-based Out-of-distribution Generation
72. ICML 2023Extrapolative Controlled Sequence Generation via Iterative Refinement
73. ICML 2023Fair Neighbor Embedding
74. ICML 2023Improved Learning-Augmented Algorithms for the Multi-Option Ski Rental Problem via Best-Possible Competitive Analysis
75. ICML 2023IncDSI: Incrementally Updatable Document Retrieval
76. ICML 2023Paging with Succinct Predictions
77. ICML 2023Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
78. ICML 2023Protecting Language Generation Models via Invisible Watermarking
79. ICML 2023Repository-Level Prompt Generation for Large Language Models of Code
80. ICML 2023Retrieval-Augmented Multimodal Language Modeling
81. ICML 2023Tied-Augment: Controlling Representation Similarity Improves Data Augmentation
82. ICML 2023TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation
83. ICML 2023Variational Open-Domain Question Answering
84. NeurIPS 2023A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance
85. NeurIPS 2023Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
86. NeurIPS 2023FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy
87. NeurIPS 2023Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory
88. NeurIPS 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
89. NeurIPS 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
90. NeurIPS 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
91. NeurIPS 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
92. NeurIPS 2023Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context
93. NeurIPS 2023Online Ad Allocation with Predictions
94. NeurIPS 2023Pairwise GUI Dataset Construction Between Android Phones and Tablets
95. NeurIPS 2023Prompt-augmented Temporal Point Process for Streaming Event Sequence
96. NeurIPS 2023Recommender Systems with Generative Retrieval
97. NeurIPS 2023Rethinking the Role of Token Retrieval in Multi-Vector Retrieval
98. NeurIPS 2023Retrieval-Augmented Multiple Instance Learning
99. NeurIPS 2023Topological RANSAC for instance verification and retrieval without fine-tuning
100. NeurIPS 2023Uniform Convergence with Square-Root Lipschitz Loss

常见问题

2023–2026 年四大会议一共有多少篇检索增强生成论文？

共 1,200 篇，按年份分别是 2023 年 102 篇、2024 年 183 篇、2025 年 366 篇、2026 年 549 篇。

NeurIPS 2026 有多少篇检索增强生成论文？

NeurIPS 2026 有 186 篇检索增强生成论文，上一届是 136 篇。

ICLR 2026 有多少篇检索增强生成论文？

ICLR 2026 有 129 篇检索增强生成论文，上一届是 111 篇。

ICML 2026 有多少篇检索增强生成论文？

ICML 2026 有 126 篇检索增强生成论文，上一届是 57 篇。

CVPR 2026 有多少篇检索增强生成论文？

CVPR 2026 有 108 篇检索增强生成论文，上一届是 62 篇。

哪个会议的检索增强生成论文最多？

NeurIPS，2023–2026 年共 391 篇。