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 136 篇，第 2 / 3 页

51. NeurIPS 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
52. NeurIPS 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generation
53. NeurIPS 2025Interactive Cross-modal Learning for Text-3D Scene Retrieval
54. NeurIPS 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
55. NeurIPS 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
56. NeurIPS 2025Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
57. NeurIPS 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
58. NeurIPS 2025KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
59. NeurIPS 2025Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
60. NeurIPS 2025Learning to Rank for In-Context Example Retrieval
61. NeurIPS 2025Learning World Models for Interactive Video Generation
62. NeurIPS 2025Learning-Augmented Algorithms for $k$-median via Online Learning
63. NeurIPS 2025Learning-Augmented Facility Location Mechanisms for the Envy Ratio Objective
64. NeurIPS 2025Learning-Augmented Online Bidding in Stochastic Settings
65. NeurIPS 2025Learning-Augmented Online Bipartite Fractional Matching
66. NeurIPS 2025Learning-Augmented Streaming Algorithms for Correlation Clustering
67. NeurIPS 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
68. NeurIPS 2025MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
69. NeurIPS 2025Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
70. NeurIPS 2025MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
71. NeurIPS 2025MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation
72. NeurIPS 2025MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation
73. NeurIPS 2025MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
74. NeurIPS 2025Mitigating Semantic Collapse in Partially Relevant Video Retrieval
75. NeurIPS 2025MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
76. NeurIPS 2025MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
77. NeurIPS 2025MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis
78. NeurIPS 2025MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation
79. NeurIPS 2025MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
80. NeurIPS 2025MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
81. NeurIPS 2025MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
82. NeurIPS 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
83. NeurIPS 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
84. NeurIPS 2025NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
85. NeurIPS 2025Optimizing Retrieval for RAG via Reinforced Contrastive Learning
86. NeurIPS 2025PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
87. NeurIPS 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
88. NeurIPS 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
89. NeurIPS 2025QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
90. NeurIPS 2025RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
91. NeurIPS 2025RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
92. NeurIPS 2025RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation
93. NeurIPS 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
94. NeurIPS 2025Reconciling Geospatial Prediction and Retrieval via Sparse Representations
95. NeurIPS 2025Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
96. NeurIPS 2025REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
97. NeurIPS 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
98. NeurIPS 2025Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
99. NeurIPS 2025Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance
100. NeurIPS 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG

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。