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 126 篇，第 2 / 3 页

51. ICML 2026HGMem: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
52. ICML 2026Hierarchical Abstract Tree for Cross-Document Retrieval Augmented Generation
53. ICML 2026Hierarchical Retrieval at Scale: Bridging Interpretability and Efficiency
54. ICML 2026HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
55. ICML 2026How Good is Post-Hoc Watermarking With Language Model Rephrasing?
56. ICML 2026HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds
57. ICML 2026HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
58. ICML 2026InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context
59. ICML 2026Information Flow Reveals When to Trust Language Models
60. ICML 2026JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
61. ICML 2026LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
62. ICML 2026Learning with Admissibility: Robust Fuzzy Hashing for Cross-Modal Retrieval with Noisy Labels
63. ICML 2026Learning-augmented Rent-or-Buy with a Sample
64. ICML 2026Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
65. ICML 2026Less Is More: Elevating RAG via Performance-Driven Context Compression
66. ICML 2026Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
67. ICML 2026ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
68. ICML 2026Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
69. ICML 2026mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
70. ICML 2026MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
71. ICML 2026MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
72. ICML 2026MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
73. ICML 2026NAVIGATE: Evaluating Visual-Guided Search Decision-Making on the Open Web
74. ICML 2026Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
75. ICML 2026Non-Parametric Structural Priors for Geometry Theorem Prediction
76. ICML 2026Open-World LLM Logical Reasoning
77. ICML 2026Optimal Pricing for Data-Augmented AutoML Marketplaces
78. ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
79. ICML 2026Panini: Continual Learning in Token Space via Structured Memory
80. ICML 2026ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
81. ICML 2026Parsimonious Learning-Augmented Online Metric Matching
82. ICML 2026PEARL: Differentially Private and Entropy-Aware Regulated Language Generation
83. ICML 2026Predictive Prefetching for Retrieval-Augmented Generation
84. ICML 2026Prefix-Cache-Aware Data Reordering for LLM-Augmented Database Analytics
85. ICML 2026Process Reward Agents for Steering Knowledge-Intensive Reasoning
86. ICML 2026ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
87. ICML 2026ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning
88. ICML 2026Push, Pop, Parallelize: Stack-Augmented Linear Attention via the Delta Rule
89. ICML 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
90. ICML 2026RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
91. ICML 2026RADAR: Defending RAG Dynamically against Retrieval Corruption
92. ICML 2026RAG without Forgetting: Continual Query-Infused Key Memory
93. ICML 2026Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
94. ICML 2026RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated Inference
95. ICML 2026Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
96. ICML 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
97. ICML 2026Retriever Portfolios: A Principled Approach to Adaptive RAG
98. ICML 2026RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
99. ICML 2026Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label
100. ICML 2026SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning

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。