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 250 篇，第 3 / 5 页

101. ICML 2026Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
102. ICML 2026SE-GA: Memory-Augmented Self-Evolution for GUI Agents
103. ICML 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
104. ICML 2026Self-Augmenting Retrieval for Diffusion Language Models
105. ICML 2026Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation
106. ICML 2026Small Agent Group is the Future of Digital Health
107. ICML 2026Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
108. ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
109. ICML 2026Text Has Curvature
110. ICML 2026Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents
111. ICML 2026TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
112. ICML 2026The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents
113. ICML 2026The First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning
114. ICML 2026Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
115. ICML 2026TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
116. ICML 2026Token-Free Hierarchical Indexing for RAG beyond LLM-based Summarization
117. ICML 2026Towards Optimal Robustness in Learning-Augmented Paging
118. ICML 2026Towards Whole-corpus Reconstruction of Heterogeneous RAG Knowledge Bases
119. ICML 2026Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
120. ICML 2026Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
121. ICML 2026Unveiling the Role of Data Uncertainty in Tabular Deep Learning
122. ICML 2026Very Efficient Listwise Multimodal Reranking for Long Documents
123. ICML 2026VideoTrace-R1: Long Video-based Retrieval-Augmented Generation via Reinforcement Learning
124. ICML 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
125. ICML 2026When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
126. ICML 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
127. ICML 2025Algorithms and Hardness for Active Learning on Graphs
128. ICML 2025Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees
129. ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
130. ICML 2025Attention-Level Speculation
131. ICML 2025AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
132. ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
133. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
134. ICML 2025Contradiction Retrieval via Contrastive Learning with Sparsity
135. ICML 2025Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
136. ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
137. ICML 2025Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
138. ICML 2025EgoPrivacy: What Your First-Person Camera Says About You?
139. ICML 2025EPIC: Efficient Position-Independent Caching for Serving Large Language Models
140. ICML 2025Equivariant Neural Tangent Kernels
141. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
142. ICML 2025From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
143. ICML 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
144. ICML 2025Graph World Model
145. ICML 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
146. ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
147. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
148. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
149. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
150. ICML 2025LAuReL: Learned Augmented Residual Layer

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。