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 16 / 24 页

  1. ICML 2025Locality Preserving Markovian Transition for Instance Retrieval
  2. ICML 2025MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification
  3. ICML 2025Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems
  4. ICML 2025Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning
  5. ICML 2025On the Power of Learning-Augmented Search Trees
  6. ICML 2025On the Query Complexity of Verifier-Assisted Language Generation
  7. ICML 2025On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
  8. ICML 2025Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
  9. ICML 2025PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
  10. ICML 2025PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
  11. ICML 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
  12. ICML 2025Position: Retrieval-augmented systems can be dangerous medical communicators
  13. ICML 2025QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
  14. ICML 2025RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  15. ICML 2025RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding
  16. ICML 2025Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
  17. ICML 2025RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
  18. ICML 2025Retrieval Augmented Time Series Forecasting
  19. ICML 2025Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate
  20. ICML 2025Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
  21. ICML 2025Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
  22. ICML 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
  23. ICML 2025SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval
  24. ICML 2025SHE: Streaming-media Hashing Retrieval
  25. ICML 2025SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs
  26. ICML 2025STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
  27. ICML 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting
  28. ICML 2025Tool Unlearning for Tool-Augmented LLMs
  29. ICML 2025Understanding Synthetic Context Extension via Retrieval Heads
  30. NeurIPS 2025A Learning-Augmented Approach to Online Allocation Problems
  31. NeurIPS 2025A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
  32. NeurIPS 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
  33. NeurIPS 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding
  34. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
  35. NeurIPS 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  36. NeurIPS 2025AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
  37. NeurIPS 2025Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
  38. NeurIPS 2025Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
  39. NeurIPS 2025Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation
  40. NeurIPS 2025Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing
  41. NeurIPS 2025Boosting Knowledge Utilization in Multimodal Large Language Models via Adaptive Logits Fusion and Attention Reallocation
  42. NeurIPS 2025C-SEO Bench: Does Conversational SEO Work?
  43. NeurIPS 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
  44. NeurIPS 2025Chain-of-Retrieval Augmented Generation
  45. NeurIPS 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
  46. NeurIPS 2025Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
  47. NeurIPS 2025Compress & Cache: Vision token compression for efficient generation and retrieval
  48. NeurIPS 2025Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text
  49. NeurIPS 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers
  50. NeurIPS 2025CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming

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