Retrieval-Augmented Generation papers, 2023–2026

Key findings

• Retrieval-Augmented Generation went from 102 papers in 2023 to 549 in 2026, roughly 5.4x in three years.
• NeurIPS publishes the most Retrieval-Augmented Generation work: 391 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with AI Agents: papers tagged with both rose from 0 in 2023 to 75 in 2026.
• Among the 5 topics under Natural Language, it ranks #2 by 2026 paper count; the fastest grower in the group, Code Generation, is up 4.1x versus 5.4x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Retrieval-Augmented Generation papers

366 papers, page 7 of 8

301. NeurIPS 2025MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation
302. NeurIPS 2025MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation
303. NeurIPS 2025MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
304. NeurIPS 2025Mitigating Semantic Collapse in Partially Relevant Video Retrieval
305. NeurIPS 2025MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
306. NeurIPS 2025MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
307. NeurIPS 2025MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis
308. NeurIPS 2025MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation
309. NeurIPS 2025MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
310. NeurIPS 2025MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
311. NeurIPS 2025MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation
312. NeurIPS 2025NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge
313. NeurIPS 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
314. NeurIPS 2025NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
315. NeurIPS 2025Optimizing Retrieval for RAG via Reinforced Contrastive Learning
316. NeurIPS 2025PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
317. NeurIPS 2025ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
318. NeurIPS 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
319. NeurIPS 2025QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
320. NeurIPS 2025RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
321. NeurIPS 2025RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
322. NeurIPS 2025RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation
323. NeurIPS 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
324. NeurIPS 2025Reconciling Geospatial Prediction and Retrieval via Sparse Representations
325. NeurIPS 2025Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
326. NeurIPS 2025REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
327. NeurIPS 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
328. NeurIPS 2025Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
329. NeurIPS 2025Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance
330. NeurIPS 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
331. NeurIPS 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
332. NeurIPS 2025Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
333. NeurIPS 2025RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
334. NeurIPS 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
335. NeurIPS 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
336. NeurIPS 2025SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
337. NeurIPS 2025Seeking and Updating with Live Visual Knowledge
338. NeurIPS 2025SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval
339. NeurIPS 2025Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
340. NeurIPS 2025Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
341. NeurIPS 2025SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
342. NeurIPS 2025Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
343. NeurIPS 2025SRA-CL: Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation
344. NeurIPS 2025SSRB: Direct Natural Language Querying to Massive Heterogeneous Semi-Structured Data
345. NeurIPS 2025STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
346. NeurIPS 2025SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
347. NeurIPS 2025TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles
348. NeurIPS 2025The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
349. NeurIPS 2025Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
350. NeurIPS 2025Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy

FAQ

How many Retrieval-Augmented Generation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,200 in total: 102 in 2023, 183 in 2024, 366 in 2025, 549 in 2026.

How many Retrieval-Augmented Generation papers are at NeurIPS 2026?

NeurIPS 2026 has 186 Retrieval-Augmented Generation papers, versus 136 the year before.

How many Retrieval-Augmented Generation papers are at ICLR 2026?

ICLR 2026 has 129 Retrieval-Augmented Generation papers, versus 111 the year before.

How many Retrieval-Augmented Generation papers are at ICML 2026?

ICML 2026 has 126 Retrieval-Augmented Generation papers, versus 57 the year before.

How many Retrieval-Augmented Generation papers are at CVPR 2026?

CVPR 2026 has 108 Retrieval-Augmented Generation papers, versus 62 the year before.

Which conference publishes the most Retrieval-Augmented Generation papers?

NeurIPS, with 391 papers from 2023 to 2026.