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 57 篇，第 1 / 2 页

  1. ICML 2025Algorithms and Hardness for Active Learning on Graphs
  2. ICML 2025Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees
  3. ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
  4. ICML 2025Attention-Level Speculation
  5. ICML 2025AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
  6. ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
  7. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
  8. ICML 2025Contradiction Retrieval via Contrastive Learning with Sparsity
  9. ICML 2025Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
  10. ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
  11. ICML 2025Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
  12. ICML 2025EgoPrivacy: What Your First-Person Camera Says About You?
  13. ICML 2025EPIC: Efficient Position-Independent Caching for Serving Large Language Models
  14. ICML 2025Equivariant Neural Tangent Kernels
  15. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
  16. ICML 2025From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
  17. ICML 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
  18. ICML 2025Graph World Model
  19. ICML 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
  20. ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
  21. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
  22. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
  23. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
  24. ICML 2025LAuReL: Learned Augmented Residual Layer
  25. ICML 2025Learning multivariate Gaussians with imperfect advice
  26. ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
  27. ICML 2025Learning-Augmented Hierarchical Clustering
  28. ICML 2025Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams
  29. ICML 2025Locality Preserving Markovian Transition for Instance Retrieval
  30. ICML 2025MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification
  31. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
  32. ICML 2025Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning
  33. ICML 2025On the Power of Learning-Augmented Search Trees
  34. ICML 2025On the Query Complexity of Verifier-Assisted Language Generation
  35. ICML 2025On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
  36. ICML 2025Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
  37. ICML 2025PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
  38. ICML 2025PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
  39. ICML 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
  40. ICML 2025Position: Retrieval-augmented systems can be dangerous medical communicators
  41. ICML 2025QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
  42. ICML 2025RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  43. ICML 2025RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding
  44. ICML 2025Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
  45. ICML 2025RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
  46. ICML 2025Retrieval Augmented Time Series Forecasting
  47. ICML 2025Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
  48. ICML 2025Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
  49. ICML 2025Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
  50. ICML 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

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