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 549 篇，第 10 / 11 页

451. NeurIPS 2026KVFocus: A Perturbation-Theoretic Token-Risk Score for Selective KV Cache Reuse in RAG
452. NeurIPS 2026Latent Abstraction for Retrieval-Augmented Generation
453. NeurIPS 2026LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
454. NeurIPS 2026Learning Augmented Exact Exponential Algorithms
455. NeurIPS 2026Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
456. NeurIPS 2026Learning-Augmented Online Scheduling with Parsimonious Preemption
457. NeurIPS 2026Less Evidence, Better Answering: Gain-Aware Minimal Evidence Subset Selection for Medical QA
458. NeurIPS 2026Listening to the Retriever: Perturbation-Sensitive Question Selection for Interactive Person Retrieval
459. NeurIPS 2026LOCO: Local Light-Aware Object Compositing with Spatially Varying Illumination-Augmented Data
460. NeurIPS 2026LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting
461. NeurIPS 2026Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
462. NeurIPS 2026LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval
463. NeurIPS 2026LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
464. NeurIPS 2026Machine Learning-Driven RAG System Design
465. NeurIPS 2026ManipulationRAG: Retrieval-Augmented Fine-Grained Manipulation of Object Functional Parts
466. NeurIPS 2026Matchability-Aware Conformal Prediction for Open-Ended Language Model Generation
467. NeurIPS 2026MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale
468. NeurIPS 2026MemContract: Contract-Sensitive Evaluation for Mutable Agent Memory
469. NeurIPS 2026Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks
470. NeurIPS 2026Memory Retrieval for Changing Preferences
471. NeurIPS 2026MemTailor: Hierarchical Memory-Augmented Multi-Expert Learning for Long-Tailed Recognition
472. NeurIPS 2026MiniPIC: Flexible Position-Independent Caching in <100LOC
473. NeurIPS 2026Mixture of Attribute-Aware Attention Experts for Fine-grained E-Commerce Composed Image Retrieval
474. NeurIPS 2026MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocol
475. NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
476. NeurIPS 2026MoRe-DVC: Motion Retrieval-Augmented Generation for Detailed Video Captioning
477. NeurIPS 2026Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference
478. NeurIPS 2026OfficeInstruct: A Dataset for Tool-Augmented Office Agents on Long-Trajectory Generative Tasks
479. NeurIPS 2026OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation
480. NeurIPS 2026OmniMemBench: Towards Scalable Evaluation of Long-Term Omni-Modal Agent Memory
481. NeurIPS 2026On objective mismatch in molecular retrieval from tandem mass spectrometry
482. NeurIPS 2026On the Price of Privacy for Language Identification and Generation
483. NeurIPS 2026On-Policy Distillation with Open Property-Equivalence Reward for LLM-Based NL-to-SVA Generation
484. NeurIPS 2026One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation
485. NeurIPS 2026OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation
486. NeurIPS 2026Optimal Real-Data Allocation for Synthetic-Data-Augmented Inference
487. NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
488. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
489. NeurIPS 2026Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
490. NeurIPS 2026PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
491. NeurIPS 2026PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
492. NeurIPS 2026Phase-wise MLLM Tuning for Multi-framework WebUI Code Generation
493. NeurIPS 2026Position: Reconciling Open Access with Owner Control in AI Model Distribution Deserves More Research Effort
494. NeurIPS 2026Prediction-Augmented Trees for Reliable Statistical Inference
495. NeurIPS 2026Privacy-Preserving Retrieval-Augmented Generation with Plausible Deniability
496. NeurIPS 2026Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models
497. NeurIPS 2026ProSearch: Benchmarking Multi-Constraint Protocol Retrieval in Experimental Science
498. NeurIPS 2026RAG in a Trenchcoat: When Minimal Memory Is Enough for Agentic Systems, and When It Isn’t
499. NeurIPS 2026RAGBoost: Robust Tabular Learning via Retrieval-Augmented and Ancillary-Guided Gradient Boosting
500. NeurIPS 2026RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance

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。