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 366 篇，第 4 / 8 页

  1. ICLR 2025SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
  2. ICLR 2025SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback
  3. ICLR 2025Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
  4. ICLR 2025STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning
  5. ICLR 2025StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
  6. ICLR 2025Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
  7. ICLR 2025SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
  8. ICLR 2025Synthetic continued pretraining
  9. ICLR 2025TabM: Advancing tabular deep learning with parameter-efficient ensembling
  10. ICLR 2025Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency
  11. ICLR 2025Test-time Adaptation for Cross-modal Retrieval with Query Shift
  12. ICLR 2025Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
  13. ICLR 2025To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
  14. ICLR 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
  15. ICLR 2025Training Large Language Models for Retrieval-Augmented Question Answering through Backtracking Correction
  16. ICLR 2025Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors
  17. ICLR 2025VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
  18. ICLR 2025Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark
  19. ICLR 2025VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation
  20. ICLR 2025Ward: Provable RAG Dataset Inference via LLM Watermarks
  21. ICLR 2025WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning
  22. ICLR 2025YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
  23. ICLR 2025Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks
  24. ICML 2025Algorithms and Hardness for Active Learning on Graphs
  25. ICML 2025Approximate Forest Completion and Learning-Augmented Algorithms for Metric Minimum Spanning Trees
  26. ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
  27. ICML 2025Attention-Level Speculation
  28. ICML 2025AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
  29. ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
  30. ICML 2025CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance
  31. ICML 2025Contradiction Retrieval via Contrastive Learning with Sparsity
  32. ICML 2025Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering
  33. ICML 2025DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning
  34. ICML 2025Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
  35. ICML 2025EgoPrivacy: What Your First-Person Camera Says About You?
  36. ICML 2025EPIC: Efficient Position-Independent Caching for Serving Large Language Models
  37. ICML 2025Equivariant Neural Tangent Kernels
  38. ICML 2025Explaining the role of Intrinsic Dimensionality in Adversarial Training
  39. ICML 2025From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
  40. ICML 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
  41. ICML 2025Graph World Model
  42. ICML 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
  43. ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
  44. ICML 2025L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning
  45. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
  46. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
  47. ICML 2025LAuReL: Learned Augmented Residual Layer
  48. ICML 2025Learning multivariate Gaussians with imperfect advice
  49. ICML 2025Learning-Augmented Algorithms for MTS with Bandit Access to Multiple Predictors
  50. ICML 2025Learning-Augmented Hierarchical Clustering

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