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 366 篇，第 1 / 8 页

1. CVPR 2025AirRoom: Objects Matter in Room Reidentification
2. CVPR 2025AKiRa: Augmentation Kit on Rays for Optical Video Generation
3. CVPR 2025ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
4. CVPR 2025ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary
5. CVPR 2025Augmented Deep Contexts for Spatially Embedded Video Coding
6. CVPR 2025BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation
7. CVPR 2025Boosting Adversarial Transferability through Augmentation in Hypothesis Space
8. CVPR 2025Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
9. CVPR 2025CCIN: Compositional Conflict Identification and Neutralization for Composed Image Retrieval
10. CVPR 2025Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment
11. CVPR 2025ChatHuman: Chatting about 3D Humans with Tools
12. CVPR 2025CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
13. CVPR 2025COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
14. CVPR 2025Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation
15. CVPR 2025ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
16. CVPR 2025DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation
17. CVPR 2025Docopilot: Improving Multimodal Models for Document-Level Understanding
18. CVPR 2025Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents
19. CVPR 2025DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
20. CVPR 2025Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
21. CVPR 2025Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
22. CVPR 2025FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
23. CVPR 2025From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
24. CVPR 2025Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval
25. CVPR 2025GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation
26. CVPR 2025HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation
27. CVPR 2025Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
28. CVPR 2025LaTexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending
29. CVPR 2025Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
30. CVPR 2025Learning with Noisy Triplet Correspondence for Composed Image Retrieval
31. CVPR 2025LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table
32. CVPR 2025MAD: Memory-Augmented Detection of 3D Objects
33. CVPR 2025MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation
34. CVPR 2025MaRI: Material Retrieval Integration across Domains
35. CVPR 2025MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities
36. CVPR 2025NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
37. CVPR 2025OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
38. CVPR 2025PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval
39. CVPR 2025RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings
40. CVPR 2025RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
41. CVPR 2025Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
42. CVPR 2025Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
43. CVPR 2025SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
44. CVPR 2025Scaling Mesh Generation via Compressive Tokenization
45. CVPR 2025Scene Map-based Prompt Tuning for Navigation Instruction Generation
46. CVPR 2025Search and Detect: Training-Free Long Tail Object Detection via Web-Image Retrieval
47. CVPR 2025Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
48. CVPR 2025SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
49. CVPR 2025SerialGen: Personalized Image Generation by First Standardization Then Personalization
50. CVPR 2025SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons

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。