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 1,200 篇，第 2 / 24 页

51. CVPR 2026MeshWeaver Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation
52. CVPR 2026MotionMaster Generalizable Text-Driven Motion Generation and Editing
53. CVPR 2026MR-RAG Multimodal Relevance-Aware Retrieval-Augmented Generation for Medical Visual Question Answering
54. CVPR 2026MRD Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
55. CVPR 2026Multi-view Consistent 3D Gaussian Head Avatars without Multi-view Generation
56. CVPR 2026MUSE Harnessing Precise and Diverse Semantics for Few-Shot Whole Slide
57. CVPR 2026Nestwork Conditional 3D Furnished House Layout Generation through Latent Heterogeneous
58. CVPR 2026Not All Birds Look The Same Identity-Preserving Generation For Birds
59. CVPR 2026One-to-More High-Fidelity Training-Free Anomaly Generation with Attention Control
60. CVPR 2026OpenT2M No-frill Motion Generation with Open-source Large-scale High-quality Data
61. CVPR 2026Photo3D Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement
62. CVPR 2026PinPoint Evaluation of Composed Image Retrieval with Explicit Negatives Multi-Image
63. CVPR 2026Plenoptic Video Generation
64. CVPR 2026POGA Paraphrased and Oppositional Graph Alignment for Fine-Grained Cross-Modal Retrieval
65. CVPR 2026PoseMaster A Unified 3D Native Framework for Stylized Pose Generation
66. CVPR 2026Progressive Neural Architecture Generation
67. CVPR 2026Quota-Calibrated Fine-Grained Alignment with Context-Aware Marginals for Text-based Person Retrieval
68. CVPR 2026R4 Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space
69. CVPR 2026R4-CGQA Retrieval-based Vision Language Models for Computer Graphics Image Quality
70. CVPR 2026RAG-TP A General Framework for Vehicle Trajectory Prediction via Retrieval-Augmented
71. CVPR 2026RAGTrack Language-aware RGBT Tracking with Retrieval-Augmented Generation
72. CVPR 2026RAID Retrieval-Augmented Anomaly Detection
73. CVPR 2026ReAG Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
74. CVPR 2026Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge Bases
75. CVPR 2026ReMatch Boosting Representation through Matching for Multimodal Retrieval
76. CVPR 2026Resolving Evidence Sparsity Agentic Context Engineering for Long-Document Understanding
77. CVPR 2026RetFormer Multimodal Retrieval for Enhancing Image Recognition
78. CVPR 2026Retrieve and Segment Are a Few Examples Enough to Bridge
79. CVPR 2026Retrieve-to-Restore Efficient All-in-One Image Restoration with a Retrieval-Based Degradation Bank
80. CVPR 2026Retrieving Counterfactuals Improves Visual In-Context Learning
81. CVPR 2026RI-Mamba Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval
82. CVPR 2026Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence
83. CVPR 2026RobustVisRAG Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations
84. CVPR 2026SAR2Net Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain Alignment
85. CVPR 2026SAT-RRG LLM-Guided Self-Adaptive Training for Radiology Report Generation with Token-Level
86. CVPR 2026Say Cheese Detail-Preserving Portrait Collection Generation via Natural Language Edits
87. CVPR 2026SceneMaker Open-set 3D Scene Generation with Decoupled De-occlusion and Pose
88. CVPR 2026Scone Bridging Composition and Distinction in Subject-Driven Image Generation via
89. CVPR 2026Seeing the Scene Matters Revealing Forgetting in Video Understanding Models
90. CVPR 2026Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation
91. CVPR 2026SIMPLEPOSTER A SIMPLE BASELINE FOR PRODUCT POSTER GENERATION
92. CVPR 2026Spatial Retrieval Augmented Autonomous Driving
93. CVPR 2026SRA-Det Learning Omni-Grained Open-Vocabulary Detection Beyond Category Names
94. CVPR 2026StreamRAG Enhancing Real-Time Video Understanding with Retrieval Augmentation
95. CVPR 2026Tackling Alignment Ambiguity in Person Retrieval through Conversational Attribute Mining
96. CVPR 2026Temporal Equilibrium MeanFlow Bridging the Scale Gap for One-Step Generation
97. CVPR 2026Think Before You Drive World Model-Inspired Multimodal Grounding
98. CVPR 2026Thinking Beyond Labels Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
99. CVPR 2026TIGER A Unified Framework for Time Images and Geo-location Retrieval
100. CVPR 2026Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization

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。