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 111 篇，第 1 / 3 页

1. ICLR 2025A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
2. ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
3. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
4. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
5. ICLR 2025Agent S: An Open Agentic Framework that Uses Computers Like a Human
6. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
7. ICLR 2025Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
8. ICLR 2025Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation
9. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
10. ICLR 2025Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
11. ICLR 2025Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
12. ICLR 2025Block-Attention for Efficient Prefilling
13. ICLR 2025Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
14. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
15. ICLR 2025Chunk-Distilled Language Modeling
16. ICLR 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
17. ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
18. ICLR 2025Contextual Document Embeddings
19. ICLR 2025Contextualizing biological perturbation experiments through language
20. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
21. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
22. ICLR 2025DataGen: Unified Synthetic Dataset Generation via Large Language Models
23. ICLR 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
24. ICLR 2025DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
25. ICLR 2025DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
26. ICLR 2025Eliminating Position Bias of Language Models: A Mechanistic Approach
27. ICLR 2025Episodic Memories Generation and Evaluation Benchmark for Large Language Models
28. ICLR 2025ESE: Espresso Sentence Embeddings
29. ICLR 2025FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
30. ICLR 2025Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
31. ICLR 2025From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
32. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
33. ICLR 2025Generative Representational Instruction Tuning
34. ICLR 2025GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
35. ICLR 2025HELMET: How to Evaluate Long-context Models Effectively and Thoroughly
36. ICLR 2025Herald: A Natural Language Annotated Lean 4 Dataset
37. ICLR 2025Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
38. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
39. ICLR 2025HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction
40. ICLR 2025Improving Uncertainty Estimation through Semantically Diverse Language Generation
41. ICLR 2025Inference Scaling for Long-Context Retrieval Augmented Generation
42. ICLR 2025InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales
43. ICLR 2025Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
44. ICLR 2025KBLaM: Knowledge Base augmented Language Model
45. ICLR 2025KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA
46. ICLR 2025LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
47. ICLR 2025Learn-by-interact: A Data-Centric Framework For Self-Adaptive Agents in Realistic Environments
48. ICLR 2025Learning-Augmented Frequent Directions
49. ICLR 2025Logical Consistency of Large Language Models in Fact-Checking
50. ICLR 2025Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in 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。