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 3 / 4 页

101. NeurIPS 2026Machine Learning-Driven RAG System Design
102. NeurIPS 2026ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
103. NeurIPS 2026Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
104. NeurIPS 2026MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
105. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
106. NeurIPS 2026Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
107. NeurIPS 2026Memory Retrieval for Changing Preferences
108. NeurIPS 2026MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
109. NeurIPS 2026MiniPIC: Flexible Position-Independent Caching in <100LOC
110. NeurIPS 2026Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval
111. NeurIPS 2026MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
112. NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
113. NeurIPS 2026MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
114. NeurIPS 2026Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
115. NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
116. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
117. NeurIPS 2026OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
118. NeurIPS 2026On objective mismatch in molecular retrieval from tandem mass spectrometry
119. NeurIPS 2026On the Price of Privacy for Language Identification and Generation
120. NeurIPS 2026On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
121. NeurIPS 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
122. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
123. NeurIPS 2026Optimal Real-Data Allocation for Synthetic-Data-Augmented Inference
124. NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
125. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
126. NeurIPS 2026Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
127. NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
128. NeurIPS 2026PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
129. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
130. NeurIPS 2026Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
131. NeurIPS 2026Prediction-Augmented Trees for Reliable Statistical Inference
132. NeurIPS 2026Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
133. NeurIPS 2026Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
134. NeurIPS 2026ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
135. NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
136. NeurIPS 2026RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
137. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance
138. NeurIPS 2026ReCon: Toward Balanced Learning under Inter-Context and Context-Memory Conflicts
139. NeurIPS 2026REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic Bridge
140. NeurIPS 2026Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees
141. NeurIPS 2026Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
142. NeurIPS 2026Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks
143. NeurIPS 2026Retrieve What’s Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation
144. NeurIPS 2026Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
145. NeurIPS 2026REVERSE: Reinforcing Evidence Verification and Search for Agentic Image Geolocation
146. NeurIPS 2026RIVET: Regex-to-Indexable Keys via Neural Translation for Interactive LIMIT-k Retrieval
147. NeurIPS 2026RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-𝑁 Ranking
148. NeurIPS 2026RTCBench: Evaluating Tool Use of Large Language Models Beyond Oracle Access
149. NeurIPS 2026RTEB: An Overfitting-Resistant Benchmark for Embedding Model Evaluation
150. NeurIPS 2026SAFTAC: Simulation-Augmented Fine-Tuning of Open-Source LLMs for Analog Circuit Design

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。