检索增强生成论文趋势 2023–2026

主要结论

• 检索增强生成论文从 2023 年的 102 篇增长到 2026 年的 549 篇，三年间扩大到约 5.4 倍。
• NeurIPS 是发检索增强生成论文最多的会议，2023–2026 年共 391 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 75 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的代码生成是 4.1 倍，检索增强生成是 5.4 倍。

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

• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
• ICLR 2026AdaCache: Adaptive Caching and Context Augmentation for Efficient LLM Serving
• CVPR 2026ADSeeker A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and
• NeurIPS 2025AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
• ICML 2025Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
• ICLR 2025A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
• CVPR 2025AirRoom: Objects Matter in Room Reidentification
• NeurIPS 2024$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
• ICML 2024A Statistical Framework for Data-dependent Retrieval-Augmented Models
• ICLR 2024BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
• CVPR 2024Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods
• NeurIPS 2023A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance
• ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
• ICLR 2023Decompositional Generation Process for Instance-Dependent Partial Label Learning
• CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
• NeurIPS 2026Accelerating Neural Network Training with Augmented Koopman Dynamics
• ICML 2026$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
• ICLR 2026Aria: an Agent for Retrieval and Iterative Auto-Formalization via Dependency Graph
• CVPR 2026Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

全部检索增强生成论文

共 1,200 篇，第 8 / 24 页

351. ICML 2026Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
352. ICML 2026TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
353. ICML 2026Token-Free Hierarchical Indexing for RAG beyond LLM-based Summarization
354. ICML 2026Towards Optimal Robustness in Learning-Augmented Paging
355. ICML 2026Towards Whole-corpus Reconstruction of Heterogeneous RAG Knowledge Bases
356. ICML 2026Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
357. ICML 2026Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
358. ICML 2026Unveiling the Role of Data Uncertainty in Tabular Deep Learning
359. ICML 2026Very Efficient Listwise Multimodal Reranking for Long Documents
360. ICML 2026VideoTrace-R1: Long Video-based Retrieval-Augmented Generation via Reinforcement Learning
361. ICML 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
362. ICML 2026When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
363. ICML 2026With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots
364. NeurIPS 2026A Theoretical Analysis of Test-Driven Code Generation
365. NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
366. NeurIPS 2026A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
367. NeurIPS 2026Accelerating Neural Network Training with Augmented Koopman Dynamics
368. NeurIPS 2026Adversarial Corpus Selection to Attack Subgraph Matching based Graph Retrieval
369. NeurIPS 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
370. NeurIPS 2026Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
371. NeurIPS 2026AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
372. NeurIPS 2026APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
373. NeurIPS 2026ASH: Agents that Self-Hone via Embodied Learning
374. NeurIPS 2026Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling
375. NeurIPS 2026Assessing Sample Quality in Conditional Generation under Compositional Shift
376. NeurIPS 2026Augmented Equivariant Mesh Networks for Anatomical Segmentation
377. NeurIPS 2026Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs
378. NeurIPS 2026Augmented Lagrangian Predictive Coding
379. NeurIPS 2026Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
380. NeurIPS 2026Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models
381. NeurIPS 2026Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport
382. NeurIPS 2026Beyond Flat Walks: Compositional Abstraction for Autoregressive Graph Generation
383. NeurIPS 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
384. NeurIPS 2026Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation
385. NeurIPS 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
386. NeurIPS 2026Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes
387. NeurIPS 2026Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG
388. NeurIPS 2026BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging
389. NeurIPS 2026Boosting Brain-to-Image Decoding with TRIBE v2 Data Augmentation
390. NeurIPS 2026Boundary-Induced Forgetting in Large Language Model Tool Chains: Measuring Field-Routing Failures
391. NeurIPS 2026Breaking Noise Shortcuts in Self-Supervised Learning via Noise-Aligned View Generation
392. NeurIPS 2026BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization
393. NeurIPS 2026Can LLMs Take Retrieved Information with a Grain of Salt?
394. NeurIPS 2026Character Mixing for Video Generation
395. NeurIPS 2026CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
396. NeurIPS 2026Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
397. NeurIPS 2026Conflict-Suppressed RAG: A Simple Decoding-Time Framework for Faithful Retrieval-Augmented Generation
398. NeurIPS 2026Constraint Retrieval Is Not Constraint Enforcement in Large Language Models
399. NeurIPS 2026Contrastive Identification and Generation in the Limit
400. NeurIPS 2026Contrastive Retrieval Heads for Improved Attention-Based Reranking

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。