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 303 篇，第 3 / 7 页

101. ICLR 2026Reusing Pre-Training Data at Test Time is a Compute Multiplier
102. ICLR 2026Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
103. ICLR 2026Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
104. ICLR 2026Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
105. ICLR 2026Seq vs Seq: An Open Suite of Paired Encoders and Decoders
106. ICLR 2026ShapeGen4D: Towards High Quality 4D Shape Generation from Videos
107. ICLR 2026Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems
108. ICLR 2026SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
109. ICLR 2026StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering
110. ICLR 2026SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving
111. ICLR 2026SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models
112. ICLR 2026Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
113. ICLR 2026TokMem: Tokenized Procedural Memory for Large Language Models
114. ICLR 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
115. ICLR 2026Topology Matters in RTL Circuit Representation Learning
116. ICLR 2026Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering
117. ICLR 2026Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk
118. ICLR 2026Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders
119. ICLR 2026Towards Knowledge‑and‑Data‑Driven Organic Reaction Prediction: RAG‑Enhanced and Reasoning‑Powered Hybrid System with LLMs
120. ICLR 2026U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs
121. ICLR 2026Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
122. ICLR 2026Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge
123. ICLR 2026Unified Multi-Modal Interactive and Reactive 3D Motion Generation via Rectified Flow
124. ICLR 2026Video-As-Prompt: Unified Semantic Control for Video Generation
125. ICLR 2026WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection
126. ICLR 2026Welfarist Formulations for Diverse Similarity Search
127. ICLR 2026When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented Generation
128. ICLR 2026Your Language Model Secretly Contains Personality Subnetworks
129. ICLR 2026Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
130. ICLR 2025A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
131. ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
132. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
133. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
134. ICLR 2025Agent S: An Open Agentic Framework that Uses Computers Like a Human
135. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
136. ICLR 2025Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
137. ICLR 2025Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation
138. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
139. ICLR 2025Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
140. ICLR 2025Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
141. ICLR 2025Block-Attention for Efficient Prefilling
142. ICLR 2025Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
143. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
144. ICLR 2025Chunk-Distilled Language Modeling
145. ICLR 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
146. ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
147. ICLR 2025Contextual Document Embeddings
148. ICLR 2025Contextualizing biological perturbation experiments through language
149. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
150. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

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。