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 549 篇，第 7 / 11 页

  1. ICML 2026Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
  2. ICML 2026Less Is More: Elevating RAG via Performance-Driven Context Compression
  3. ICML 2026Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
  4. ICML 2026ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
  5. ICML 2026Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
  6. ICML 2026mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
  7. ICML 2026MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier
  8. ICML 2026MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
  9. ICML 2026MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
  10. ICML 2026NAVIGATE: Evaluating Visual-Guided Search Decision-Making on the Open Web
  11. ICML 2026Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
  12. ICML 2026Non-Parametric Structural Priors for Geometry Theorem Prediction
  13. ICML 2026Open-World LLM Logical Reasoning
  14. ICML 2026Optimal Pricing for Data-Augmented AutoML Marketplaces
  15. ICML 2026Optimizing Agentic Reasoning with Retrieval via Synthetic Semantic Information Gain Reward
  16. ICML 2026Panini: Continual Learning in Token Space via Structured Memory
  17. ICML 2026ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
  18. ICML 2026Parsimonious Learning-Augmented Online Metric Matching
  19. ICML 2026PEARL: Differentially Private and Entropy-Aware Regulated Language Generation
  20. ICML 2026Predictive Prefetching for Retrieval-Augmented Generation
  21. ICML 2026Prefix-Cache-Aware Data Reordering for LLM-Augmented Database Analytics
  22. ICML 2026Process Reward Agents for Steering Knowledge-Intensive Reasoning
  23. ICML 2026ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
  24. ICML 2026ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning
  25. ICML 2026Push, Pop, Parallelize: Stack-Augmented Linear Attention via the Delta Rule
  26. ICML 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
  27. ICML 2026RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
  28. ICML 2026RADAR: Defending RAG Dynamically against Retrieval Corruption
  29. ICML 2026RAG without Forgetting: Continual Query-Infused Key Memory
  30. ICML 2026Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
  31. ICML 2026RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated Inference
  32. ICML 2026Reranker Helps, but Not Enough: Towards Strong Poisoning Attacks Against Retrieval-Augmented Generation
  33. ICML 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
  34. ICML 2026Retriever Portfolios: A Principled Approach to Adaptive RAG
  35. ICML 2026RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
  36. ICML 2026Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label
  37. ICML 2026SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning
  38. ICML 2026Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs
  39. ICML 2026SE-GA: Memory-Augmented Self-Evolution for GUI Agents
  40. ICML 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
  41. ICML 2026Self-Augmenting Retrieval for Diffusion Language Models
  42. ICML 2026Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation
  43. ICML 2026Small Agent Group is the Future of Digital Health
  44. ICML 2026Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
  45. ICML 2026Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
  46. ICML 2026Text Has Curvature
  47. ICML 2026Textual Stochastic Gradient Descent: Discrete Optimization of External Memory for Reasoning Language Agents
  48. ICML 2026TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
  49. ICML 2026The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents
  50. ICML 2026The First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning

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