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 391 篇，第 2 / 8 页

  1. NeurIPS 2026Dynamic Regulatory Graph Learning for Histology-to-Spatial Transcriptomics
  2. NeurIPS 2026Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
  3. NeurIPS 2026Exact Regular-Constrained Sampling for Variable-Order Markov Generation
  4. NeurIPS 2026Expanding Flow Maps
  5. NeurIPS 2026Exposing Private Corpus Leakage in Multimodal RAG
  6. NeurIPS 2026FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
  7. NeurIPS 2026Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
  8. NeurIPS 2026Feeling of Knowing in Large Language Models
  9. NeurIPS 2026Firefly: Illuminating Verified Real-world Tool Call Data Generation
  10. NeurIPS 2026FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
  11. NeurIPS 2026FracTS: Hierarchical and Autoregressive Time Series Generation
  12. NeurIPS 2026G-Zero: Self-Play for Open-Ended Generation from Zero Data
  13. NeurIPS 2026Generating the Unheard: Phylogeny-Guided Latent Generation for Ancestral Sound Reconstruction
  14. NeurIPS 2026Generation-Drift-Guided Block Pruning for Large Language Models
  15. NeurIPS 2026GeoFidelity-Bench: Evaluating Block-Conditioned Geographic Fidelity in Text-to-Image Street-View Generation
  16. NeurIPS 2026Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG
  17. NeurIPS 2026Gradient Boosted Trees for Retrieval-Augmented Generation
  18. NeurIPS 2026GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
  19. NeurIPS 2026GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
  20. NeurIPS 2026Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
  21. NeurIPS 2026Half-Truths Break Similarity-Based Retrieval
  22. NeurIPS 2026HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models
  23. NeurIPS 2026HALO: Homotopy-Augmented Layer Optimization for Stable LLM Supervised Post-training
  24. NeurIPS 2026HARMONY: Hierarchical Anchor Retrieval on Manifold for Oblivious-source Acoustic Anomaly Detection
  25. NeurIPS 2026How Data Augmentation Shapes Neural Representations
  26. NeurIPS 2026How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?
  27. NeurIPS 2026Hypothesis generation and updating in large language models
  28. NeurIPS 2026I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
  29. NeurIPS 2026IADR: Interface-Augmented Neural Operator for Phase-Field Mean-Curvature Flow
  30. NeurIPS 2026In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
  31. NeurIPS 2026Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
  32. NeurIPS 2026IndustryCode: A Benchmark for Industry Code Generation
  33. NeurIPS 2026Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
  34. NeurIPS 2026Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate
  35. NeurIPS 2026Is Dimensionality a Barrier for Retrieval Models?
  36. NeurIPS 2026Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
  37. NeurIPS 2026Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
  38. NeurIPS 2026KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
  39. NeurIPS 2026Latent Abstraction for Retrieval-Augmented Generation
  40. NeurIPS 2026LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
  41. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
  42. NeurIPS 2026Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
  43. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
  44. NeurIPS 2026Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
  45. NeurIPS 2026Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
  46. NeurIPS 2026LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
  47. NeurIPS 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
  48. NeurIPS 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
  49. NeurIPS 2026LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
  50. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

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