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 186 篇，第 2 / 4 页

51. NeurIPS 2026Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics
52. NeurIPS 2026Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
53. NeurIPS 2026Exact Regular-Constrained Sampling for Variable-Order Markov Generation
54. NeurIPS 2026Expanding Flow Maps
55. NeurIPS 2026Exposing Private Corpus Leakage in Multimodal RAG
56. NeurIPS 2026FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
57. NeurIPS 2026Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
58. NeurIPS 2026Feeling of Knowing in Large Language Models
59. NeurIPS 2026Firefly: Illuminating Verified Real-world Tool Call Data Generation
60. NeurIPS 2026FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
61. NeurIPS 2026FracTS: Hierarchical and Autoregressive Time Series Generation
62. NeurIPS 2026G-Zero: Self-Play for Open-Ended Generation from Zero Data
63. NeurIPS 2026Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
64. NeurIPS 2026Generation-Drift-Guided Block Pruning for Large Language Models
65. NeurIPS 2026GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity in Text-to-Image Street-View Generation
66. NeurIPS 2026Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG
67. NeurIPS 2026Gradient Boosted Trees for Retrieval-Augmented Generation
68. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
69. NeurIPS 2026GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
70. NeurIPS 2026Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
71. NeurIPS 2026Half-Truths Break Similarity-Based Retrieval
72. NeurIPS 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
73. NeurIPS 2026HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training
74. NeurIPS 2026HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly Detection
75. NeurIPS 2026How Data Augmentation Shapes Neural Representations
76. NeurIPS 2026How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?
77. NeurIPS 2026Hypothesis generation and updating in large language models
78. NeurIPS 2026I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
79. NeurIPS 2026IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow
80. NeurIPS 2026In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
81. NeurIPS 2026Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
82. NeurIPS 2026IndustryCode: A Benchmark for Industry Code Generation
83. NeurIPS 2026Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
84. NeurIPS 2026Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
85. NeurIPS 2026Is Dimensionality a Barrier for Retrieval Models?
86. NeurIPS 2026Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
87. NeurIPS 2026Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
88. NeurIPS 2026KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
89. NeurIPS 2026Latent Abstraction for Retrieval-Augmented Generation
90. NeurIPS 2026LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
91. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
92. NeurIPS 2026Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
93. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
94. NeurIPS 2026Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
95. NeurIPS 2026Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
96. NeurIPS 2026LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
97. NeurIPS 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
98. NeurIPS 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
99. NeurIPS 2026LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
100. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

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。