检索增强生成论文趋势 2023–2026

RAG 与检索增强

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,200 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

检索增强生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202319291737102
202450345049183
20251361115762366
2026186129126108549

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

全部检索增强生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,200 篇，第 13 / 24 页

  1. CVPR 2025Structured 3D Latents for Scalable and Versatile 3D Generation
  2. CVPR 2025Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
  3. CVPR 2025TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance
  4. CVPR 2025The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation
  5. CVPR 2025Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation
  6. CVPR 2025Universal Scene Graph Generation
  7. CVPR 2025VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents
  8. CVPR 2025VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary
  9. CVPR 2025Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection
  10. CVPR 2025WISNet: Pseudo Label Generation on Unbalanced and Patch Annotated Waste Images
  11. CVPR 2025WonderWorld: Interactive 3D Scene Generation from a Single Image
  12. ICLR 2025A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
  13. ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
  14. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
  15. ICLR 2025Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
  16. ICLR 2025Agent S: An Open Agentic Framework that Uses Computers Like a Human
  17. ICLR 2025APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
  18. ICLR 2025Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
  19. ICLR 2025Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation
  20. ICLR 2025BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
  21. ICLR 2025Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
  22. ICLR 2025Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models
  23. ICLR 2025Block-Attention for Efficient Prefilling
  24. ICLR 2025Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
  25. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
  26. ICLR 2025Chunk-Distilled Language Modeling
  27. ICLR 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Design
  28. ICLR 2025ColPali: Efficient Document Retrieval with Vision Language Models
  29. ICLR 2025Contextual Document Embeddings
  30. ICLR 2025Contextualizing biological perturbation experiments through language
  31. ICLR 2025Controllable Context Sensitivity and the Knob Behind It
  32. ICLR 2025CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking
  33. ICLR 2025DataGen: Unified Synthetic Dataset Generation via Large Language Models
  34. ICLR 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
  35. ICLR 2025DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
  36. ICLR 2025DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  37. ICLR 2025Eliminating Position Bias of Language Models: A Mechanistic Approach
  38. ICLR 2025Episodic Memories Generation and Evaluation Benchmark for Large Language Models
  39. ICLR 2025ESE: Espresso Sentence Embeddings
  40. ICLR 2025FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
  41. ICLR 2025Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
  42. ICLR 2025From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
  43. ICLR 2025GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
  44. ICLR 2025Generative Representational Instruction Tuning
  45. ICLR 2025GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
  46. ICLR 2025HELMET: How to Evaluate Long-context Models Effectively and Thoroughly
  47. ICLR 2025Herald: A Natural Language Annotated Lean 4 Dataset
  48. ICLR 2025Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
  49. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
  50. ICLR 2025HyperPLR: Hypergraph Generation through Projection, Learning, and Reconstruction

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查检索增强生成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "retrieval-augmented-generation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「自然语言」下的其他主题