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 111 篇，第 2 / 3 页

51. ICLR 2025LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
52. ICLR 2025Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models
53. ICLR 2025MADGEN: Mass-Spec attends to De Novo Molecular generation
54. ICLR 2025MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
55. ICLR 2025MagicPIG: LSH Sampling for Efficient LLM Generation
56. ICLR 2025MAI: A Multi-turn Aggregation-Iteration Model for Composed Image Retrieval
57. ICLR 2025Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
58. ICLR 2025MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
59. ICLR 2025MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
60. ICLR 2025MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
61. ICLR 2025MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
62. ICLR 2025Multi-Field Adaptive Retrieval
63. ICLR 2025NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval
64. ICLR 2025NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions
65. ICLR 2025OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
66. ICLR 2025Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
67. ICLR 2025Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
68. ICLR 2025PICASO: Permutation-Invariant Context Composition with State Space Models
69. ICLR 2025Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models
70. ICLR 2025Provence: efficient and robust context pruning for retrieval-augmented generation
71. ICLR 2025Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks
72. ICLR 2025RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
73. ICLR 2025RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
74. ICLR 2025RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression
75. ICLR 2025RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
76. ICLR 2025Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
77. ICLR 2025ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability
78. ICLR 2025REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
79. ICLR 2025ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing
80. ICLR 2025Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach
81. ICLR 2025Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization
82. ICLR 2025RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval
83. ICLR 2025RuAG: Learned-rule-augmented Generation for Large Language Models
84. ICLR 2025SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
85. ICLR 2025Semi-Parametric Retrieval via Binary Bag-of-Tokens Index
86. ICLR 2025SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
87. ICLR 2025Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
88. ICLR 2025Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge Distillation
89. ICLR 2025SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
90. ICLR 2025SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback
91. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
92. ICLR 2025STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
93. ICLR 2025StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
94. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
95. ICLR 2025SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
96. ICLR 2025Synthetic continued pretraining
97. ICLR 2025TabM: Advancing tabular deep learning with parameter-efficient ensembling
98. ICLR 2025Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency
99. ICLR 2025Test-time Adaptation for Cross-modal Retrieval with Query Shift
100. ICLR 2025Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

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。